dvc: bump to 1.1.7

Usually we need it to parametrize tests with, so there is no
reason to duplicate the code. I've left `local_remote` fixture
just because it is so convenient and often used in a lot of tests.

.codeclimate.yml

@@ -1,5 +1,19 @@
-languages:
-    Python: true
-
-exclude_paths:
-    - tests/
+version: "2"
+checks:
+    argument-count:
+        config:
+            threshold: 8
+    complex-logic:
+        config:
+            threshold: 6
+    file-lines:
+        config:
+            threshold: 350
+    method-complexity:
+        config:
+            threshold: 15
+    method-count:
+        config:
+            threshold: 30
+exclude_patterns:
+    - tests

.deepsource.toml

@@ -4,10 +4,6 @@ test_patterns = [
   'tests/**'
 ]
 
-exclude_patterns = [
-  'dvc/utils/compat.py'
-]
-
 [[analyzers]]
 name = 'python'
 enabled = true

.flake8

@@ -1,7 +0,0 @@
-[flake8]
-ignore =
-    E203, # Whitespace before ':'
-    E266, # Too many leading '#' for block comment
-    W503, # Line break occurred before a binary operator
-max-line-length = 79
-select = B,C,E,F,W,T4,B9

.github/FUNDING.yml

@@ -0,0 +1,3 @@
+# These are supported funding model platforms
+
+patreon: DVCorg

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,10 +1,18 @@
 ---
-name: Bug report
-about: Create a report to help us improve
-
+name: "\U0001F41B Bug Report"
+about: Create a bug report to help us improve DVC
 ---
 
+## Bug Report
 
-**Please provide information about your setup**
-DVC version(i.e. `dvc --version`), Platform and method of installation (pip, homebrew, pkg Mac, exe (Windows), DEB(Linux), RPM(Linux))
+### Please provide information about your setup
 
+**Output of `dvc version`:**
+
+```console
+$ dvc version
+```
+
+**Additional Information (if any):**
+
+If applicable, please also provide a `--verbose` output of the command, eg: `dvc add --verbose`.

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: "🤗 Need help?"
+    url: https://dvc.org/chat
+    about: If you have a question, ask us on Discord. Please join with this invite 👉

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,6 +1,5 @@
 ---
-name: Feature request
+name: "\U0001F680 Feature Request"
 about: Suggest an idea for this project
-
 ---
 

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,7 +1,7 @@
-* [ ] ❗ Have you followed the guidelines in the [Contributing to DVC](https://dvc.org/doc/user-guide/contributing/core) list?
+* [ ] ❗ I have followed the [Contributing to DVC](https://dvc.org/doc/user-guide/contributing/core) checklist.
 
-* [ ] 📖 Check this box if this PR **does not** require [documentation](https://dvc.org/doc) updates, or if it does **and** you have created a separate PR in [dvc.org](https://github.com/iterative/dvc.org) with such updates (or at least opened an issue about it in that repo). Please link below to your PR (or issue) in the [dvc.org](https://github.com/iterative/dvc.org) repo.
+* [ ] 📖 If this PR requires [documentation](https://dvc.org/doc) updates, I have created a separate PR (or issue, at least) in [dvc.org](https://github.com/iterative/dvc.org) and linked it here.
 
-* [ ] ❌ Have you checked DeepSource, CodeClimate, and other sanity checks below? We consider their findings recommendatory and don't expect everything to be addressed. Please review them carefully and fix those that actually improve code or fix bugs.
+* [ ] ❌ I will check DeepSource, CodeClimate, and other sanity checks below. (We consider them recommendatory and don't expect everything to be addressed. Please fix things that actually improve code or fix bugs.)
 
 Thank you for the contribution - we'll try to review it as soon as possible. 🙏

.github/workflows/check-patch.yaml

@@ -0,0 +1,19 @@
+name: Lint Python
+
+on: [push, pull_request]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up Python 3.8
+      uses: actions/setup-python@v1
+      with:
+        python-version: 3.8
+    - name: Install requirements
+      run: bash ./scripts/ci/install.sh
+    - name: Check Patch
+      run: ./scripts/ci/check_patch.sh

.pre-commit-config.yaml

@@ -1,17 +1,75 @@
 repos:
--   repo: https://github.com/ambv/black
+  - hooks:
+      - id: black
+        language_version: python3
+    repo: https://github.com/ambv/black
     rev: 19.10b0
+  - repo: https://github.com/asottile/seed-isort-config
+    rev: v2.1.1
     hooks:
-    - id: black
-      language_version: python3
--   repo: https://gitlab.com/pycqa/flake8
+      - id: seed-isort-config
+  - hooks:
+      - id: isort
+        language_version: python3
+    repo: https://github.com/timothycrosley/isort
+    rev: 4.3.21
+  - hooks:
+      - id: flake8
+        language_version: python3
+        additional_dependencies:
+          - flake8-bugbear
+          - flake8-comprehensions
+          - flake8-debugger
+          - flake8-string-format
+    repo: https://gitlab.com/pycqa/flake8
+    rev: 3.7.9
+  - repo: local
+    hooks:
+    - id: pylint
+      name: pylint
+      entry: pylint
+      language: system
+      types: [python]
+  - hooks:
+      - args:
+          - -i
+          - "2"
+        id: beautysh
+        language_version: python3
+    repo: https://github.com/lovesegfault/beautysh
     rev: master
-    hooks:
-    - id: flake8
-      language_version: python3
--   repo: https://github.com/lovesegfault/beautysh
-    rev: master
-    hooks:
-    - id: beautysh
-      language_version: python3
-      args: [-i, '2']  # 2-space indentaion
+  - hooks:
+      - args:
+          - git-hook
+          - pre-commit
+        entry: dvc
+        id: dvc-pre-commit
+        language: system
+        name: DVC pre-commit
+        stages:
+          - commit
+        verbose: true
+        require_serial: true
+      - args:
+          - git-hook
+          - pre-push
+        entry: dvc
+        id: dvc-pre-push
+        language: system
+        name: DVC pre-push
+        stages:
+          - push
+        require_serial: true
+      - always_run: true
+        args:
+          - git-hook
+          - post-checkout
+        entry: dvc
+        id: dvc-post-checkout
+        language: system
+        minimum_pre_commit_version: 2.2.0
+        name: DVC post-checkout
+        stages:
+          - post-checkout
+        require_serial: true
+    repo: local

.pre-commit-hooks.yaml

@@ -0,0 +1,36 @@
+- args:
+  - git-hook
+  - pre-commit
+  entry: dvc
+  id: dvc-pre-commit
+  language: python
+  language_version: python3
+  name: DVC pre-commit
+  require_serial: true
+  stages:
+  - commit
+  verbose: true
+- args:
+  - git-hook
+  - pre-push
+  entry: dvc
+  id: dvc-pre-push
+  language: python
+  language_version: python3
+  name: DVC pre-push
+  require_serial: true
+  stages:
+  - push
+- always_run: true
+  args:
+  - git-hook
+  - post-checkout
+  entry: dvc
+  id: dvc-post-checkout
+  language: python
+  language_version: python3
+  minimum_pre_commit_version: 2.2.0
+  name: DVC post-checkout
+  require_serial: true
+  stages:
+  - post-checkout

.pylintrc

@@ -15,7 +15,11 @@ ignore-patterns=
 
 # Python code to execute, usually for sys.path manipulation such as
 # pygtk.require().
-#init-hook=
+init-hook="import sys; \
+           from pathlib import Path; \
+           from pylint.config import find_pylintrc; \
+           sys.path.append(Path(find_pylintrc()).parent / 'tests');"
+
 
 # Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
 # number of processors available to use.
@@ -28,7 +32,7 @@ limit-inference-results=100
 
 # List of plugins (as comma separated values of python modules names) to load,
 # usually to register additional checkers.
-load-plugins=
+load-plugins=pylint_pytest,pylint_plugin_disable
 
 # Pickle collected data for later comparisons.
 persistent=yes
@@ -60,7 +64,16 @@ confidence=
 # --enable=similarities". If you want to run only the classes checker, but have
 # no Warning level messages displayed, use "--disable=all --enable=classes
 # --disable=W".
-disable=print-statement,
+disable=format,
+        # ^ most of them are covered by flake8,
+        # and are conventions rather than warnings or errors
+        refactoring,  # will be noisy if it starts giving suggestions
+        spelling,
+        # design is too-few-* and too-many-* checks, too-much-* for us right now
+        design,
+        # following were generated by default
+        # most of them are redundant Py3 checks for Py2+3 codebase
+        print-statement,
         parameter-unpacking,
         unpacking-in-except,
         old-raise-syntax,
@@ -139,9 +152,33 @@ disable=print-statement,
         deprecated-sys-function,
         exception-escape,
         comprehension-escape,
-        useless-object-inheritance,
-        missing-docstring,
-        bad-continuation
+        # custom disables start here
+        no-self-use,
+        invalid-name,
+        # already a check enabled for `wildcard-import`
+        unused-wildcard-import,
+        misplaced-comparison-constant,
+        # probably soon: https://github.com/iterative/dvc/issues/1843
+        logging-format-interpolation,
+        logging-fstring-interpolation,
+        # we don't have proper docstrings yet
+        # even if we do, we'll be doing it gradually
+        missing-function-docstring,
+        missing-module-docstring,
+        missing-class-docstring,
+        duplicate-code,
+        # too noisy, and detects issues even when import is inside a function
+        # see: https://github.com/PyCQA/pylint/issues/850
+        cyclic-import,
+        # isort should cover these:
+        wrong-import-order,
+        wrong-import-position,
+        ungrouped-imports,
+        multiple-imports,
+        # we use it to speedup/optimize
+        import-outside-toplevel,
+        fixme,
+
 
 # Enable the message, report, category or checker with the given id(s). You can
 # either give multiple identifier separated by comma (,) or put this option
@@ -228,7 +265,7 @@ contextmanager-decorators=contextlib.contextmanager
 # List of members which are set dynamically and missed by pylint inference
 # system, and so shouldn't trigger E1101 when accessed. Python regular
 # expressions are accepted.
-generated-members=
+generated-members=pytest.lazy_fixture,logging.TRACE,logger.trace,sys.getwindowsversion
 
 # Tells whether missing members accessed in mixin class should be ignored. A
 # mixin class is detected if its name ends with "mixin" (case insensitive).
@@ -249,7 +286,7 @@ ignore-on-opaque-inference=yes
 # List of class names for which member attributes should not be checked (useful
 # for classes with dynamically set attributes). This supports the use of
 # qualified names.
-ignored-classes=optparse.Values,thread._local,_thread._local
+ignored-classes=optparse.Values,thread._local,_thread._local,Dvcfile
 
 # List of module names for which member attributes should not be checked
 # (useful for modules/projects where namespaces are manipulated during runtime
@@ -290,7 +327,7 @@ dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
 
 # Argument names that match this expression will be ignored. Default to name
 # with leading underscore.
-ignored-argument-names=_.*|^ignored_|^unused_
+ignored-argument-names=_.*|^ignored_|^unused_|args|kwargs
 
 # Tells whether we should check for unused import in __init__ files.
 init-import=no

.restyled.yaml

@@ -9,3 +9,12 @@ restylers:
     - "**/*.py"
     interpreters:
     - python
+  - name: isort
+    image: restyled/restyler-isort:v4.3.21
+    command:
+    - isort
+    arguments: []
+    include:
+    - "**/*.py"
+    interpreters:
+    - python

.travis.yml

@@ -29,7 +29,7 @@ jobs:
     os: linux
     language: python
     python: 3.7
-    before_install:
+    before_install: bash ./scripts/ci/install.sh
     install:
     script: ./scripts/ci/check_patch.sh
   # test jobs
@@ -37,15 +37,24 @@ jobs:
     stage: test
     os: windows           # Windows 10.0.17134 N/A Build 17134
     language: shell       # 'language: python' is an error on Travis CI Windows
-  - name: "3.5 on Linux"
-    language: python
-    python: 3.5
+    env:
+      - PYTHON_VERSION=3.7.5
+      - PATH=/c/Python37:/c/Python37/Scripts:$PATH
+  - name: "3.8 on Windows"
+    os: windows           # Windows 10.0.17134 N/A Build 17134
+    language: shell       # 'language: python' is an error on Travis CI Windows
+    env:
+      - PYTHON_VERSION=3.8.0
+      - PATH=/c/Python38:/c/Python38/Scripts:$PATH
   - name: "3.6 on Linux"
     language: python
     python: 3.6
   - name: "3.7 on Linux"
     language: python
     python: 3.7
+  - name: "3.8 on Linux"
+    language: python
+    python: 3.8
   - name: "3.7 on Mac"
     os: osx
     osx_image: xcode11.3
@@ -63,6 +72,9 @@ jobs:
     language: shell
     install:
     script: ./scripts/build_windows.cmd
+    env:
+      - PYTHON_VERSION=3.7.5
+      - PATH=/c/Python37:/c/Python37/Scripts:$PATH
   - name: "Linux pkgs"
     language: python
     python: 3.7
@@ -71,11 +83,11 @@ jobs:
     script: ./scripts/build_posix.sh
   - name: "PyPI pkgs"
     language: python
-    python: 3.7
+    python: 3.8
     script: ./scripts/build_package.sh
   - name: Snapcraft snap
     language: python
-    python: 3.7
+    python: 3.8
     addons:
      snaps:
      - name: snapcraft
@@ -86,8 +98,12 @@ jobs:
      - name: lxd
        channel: stable
     env:
-    - SNAPCRAFT_IMAGE_INFO: '{"build_url": "$TRAVIS_BUILD_URL"}'
+    - SNAPCRAFT_IMAGE_INFO: |
+        '{"build_url": "$TRAVIS_JOB_WEB_URL"}'
+    - SNAPCRAFT_BUILD_ENVIRONMENT: lxd
+    - SNAPCRAFT_BUILD_INFO: 1  # https://snapcraft.io/blog/introducing-developer-notifications-for-snap-security-updates
     install:
+    - sudo usermod --append --groups lxd $USER
     - sudo /snap/bin/lxd.migrate -yes
     - sudo /snap/bin/lxd waitready
     - sudo /snap/bin/lxd init --auto
@@ -136,12 +152,19 @@ deploy:
       tags: true
       repo: iterative/dvc
       stage: build
-  - provider: snap
-    snap: dvc_*.snap
-    channel: $SNAP_CHANNEL
+  - provider: script
     skip_cleanup: true
+    script: "(echo $SNAP_TOKEN | snapcraft login --with -) && timeout 600 snapcraft push dvc_*.snap --release $SNAP_CHANNEL || echo timed out"
     on:
       all_branches: true
-      condition: "$(./scripts/ci/deploy_condition.sh dvc_*.snap) && ($TRAVIS_BRANCH = master || -n $TRAVIS_TAG)"
+      condition: "$(./scripts/ci/deploy_condition.sh dvc_*.snap) && ($TRAVIS_BRANCH = master || -n $TRAVIS_TAG) && -n $SNAP_CHANNEL"
+      repo: iterative/dvc
+      stage: build
+  - provider: script
+    skip_cleanup: true
+    script: "(echo $SNAP_TOKEN | snapcraft login --with -) && timeout 600 snapcraft push dvc_*.snap --release $SNAP_CHANNEL_MAJOR || echo timed out"
+    on:
+      all_branches: true
+      condition: "$(./scripts/ci/deploy_condition.sh dvc_*.snap) && ($TRAVIS_BRANCH = master || -n $TRAVIS_TAG) && -n $SNAP_CHANNEL_MAJOR"
       repo: iterative/dvc
       stage: build

.zenodo.json

@@ -0,0 +1,8 @@
+{
+  "title": "DVC: Data Version Control - Git for Data & Models",
+  "keywords": [
+    "data-science", "data-version-control", "machine-learning", "git",
+    "developer-tools", "reproducibility", "collaboration", "ai", "python"],
+  "contributors": [
+    {"name": "DVC team", "type": "Other", "affiliation": "Iterative"}]
+}

README.rst

@@ -1,6 +1,4 @@
-.. image:: https://dvc.org/static/img/logo-github-readme.png
-  :target: https://dvc.org
-  :alt: DVC logo
+|Banner|
 
 `Website <https://dvc.org>`_
 • `Docs <https://dvc.org/doc>`_
@@ -10,33 +8,9 @@
 • `Tutorial <https://dvc.org/doc/get-started>`_
 • `Mailing List <https://sweedom.us10.list-manage.com/subscribe/post?u=a08bf93caae4063c4e6a351f6&id=24c0ecc49a>`_
 
-.. image:: https://img.shields.io/badge/release-ok-brightgreen
-  :target: https://travis-ci.com/iterative/dvc
-  :alt: Release
+|Release| |CI| |Maintainability| |Coverage| |Donate| |DOI|
 
-.. image:: https://img.shields.io/travis/com/iterative/dvc/master?label=dev
-  :target: https://travis-ci.com/iterative/dvc
-  :alt: Travis dev branch
-
-.. image:: https://codeclimate.com/github/iterative/dvc/badges/gpa.svg
-  :target: https://codeclimate.com/github/iterative/dvc
-  :alt: Code Climate
-
-.. image:: https://codecov.io/gh/iterative/dvc/branch/master/graph/badge.svg
-  :target: https://codecov.io/gh/iterative/dvc
-  :alt: Codecov
-
-.. image:: https://img.shields.io/badge/patreon-donate-green.svg
-  :target: https://www.patreon.com/DVCorg/overview
-  :alt: Donate
-
-.. image:: https://anaconda.org/conda-forge/dvc/badges/version.svg
-  :target: https://anaconda.org/conda-forge/dvc
-  :alt: Conda-forge
-
-.. image:: https://img.shields.io/badge/snap-install-82BEA0.svg?logo=snapcraft
-  :target: https://snapcraft.io/dvc
-  :alt: Snapcraft
+|PyPI| |Packages| |Brew| |Conda| |Choco| |Snap|
 
 |
 
@@ -79,9 +53,7 @@ to store data and model files seamlessly out of Git, while preserving almost the
 were stored in Git itself. To store and share the data cache, DVC supports multiple remotes - any cloud (S3, Azure,
 Google Cloud, etc) or any on-premise network storage (via SSH, for example).
 
-.. image:: https://dvc.org/static/img/flow.gif
-   :target: https://dvc.org/static/img/flow.gif
-   :alt: how_dvc_works
+|Flowchart|
 
 The DVC pipelines (computational graph) feature connects code and data together. It is possible to explicitly
 specify all steps required to produce a model: input dependencies including data, commands to run,
@@ -119,9 +91,53 @@ Installation
 There are four options to install DVC: ``pip``, Homebrew, Conda (Anaconda) or an OS-specific package.
 Full instructions are `available here <https://dvc.org/doc/get-started/install>`_.
 
+Snap (Snapcraft/Linux)
+----------------------
+
+|Snap|
+
+.. code-block:: bash
+
+   snap install dvc --classic
+
+This corresponds to the latest tagged release.
+Add ``--beta`` for the latest tagged release candidate,
+or ``--edge`` for the latest ``master`` version.
+
+Choco (Chocolatey/Windows)
+--------------------------
+
+|Choco|
+
+.. code-block:: bash
+
+   choco install dvc
+
+Brew (Homebrew/Mac OS)
+----------------------
+
+|Brew|
+
+.. code-block:: bash
+
+   brew install dvc
+
+Conda (Anaconda)
+----------------
+
+|Conda|
+
+.. code-block:: bash
+
+   conda install -c conda-forge dvc
+
+Currently, this includes support for Python versions 2.7, 3.6 and 3.7.
+
 pip (PyPI)
 ----------
 
+|PyPI|
+
 .. code-block:: bash
 
    pip install dvc
@@ -137,36 +153,11 @@ To install the development version, run:
 
    pip install git+git://github.com/iterative/dvc
 
-Homebrew
---------
-
-.. code-block:: bash
-
-   brew install dvc
-
-
-Conda (Anaconda)
-----------------
-
-.. code-block:: bash
-
-   conda install -c conda-forge dvc
-
-Currently, this includes support for Python versions 2.7, 3.6 and 3.7.
-
-Snap (Snapcraft)
-----------------
-
-.. code-block:: bash
-
-   snap install dvc --classic
-
-This corresponds to the latest tagged release.
-Add ``--edge`` for the latest ``master`` version.
-
 Package
 -------
 
+|Packages|
+
 Self-contained packages for Linux, Windows, and Mac are available. The latest version of the packages
 can be found on the GitHub `releases page <https://github.com/iterative/dvc/releases>`_.
 
@@ -206,40 +197,43 @@ Comparison to related technologies
 
 Contributing
 ============
+
+|Maintainability| |Donate|
+
 Contributions are welcome! Please see our `Contributing Guide <https://dvc.org/doc/user-guide/contributing/core>`_ for more
 details.
 
 .. image:: https://sourcerer.io/fame/efiop/iterative/dvc/images/0
-  :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/0
-  :alt: 0
+   :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/0
+   :alt: 0
 
 .. image:: https://sourcerer.io/fame/efiop/iterative/dvc/images/1
-  :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/1
-  :alt: 1
+   :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/1
+   :alt: 1
 
 .. image:: https://sourcerer.io/fame/efiop/iterative/dvc/images/2
-  :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/2
-  :alt: 2
+   :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/2
+   :alt: 2
 
 .. image:: https://sourcerer.io/fame/efiop/iterative/dvc/images/3
-  :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/3
-  :alt: 3
+   :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/3
+   :alt: 3
 
 .. image:: https://sourcerer.io/fame/efiop/iterative/dvc/images/4
-  :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/4
-  :alt: 4
+   :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/4
+   :alt: 4
 
 .. image:: https://sourcerer.io/fame/efiop/iterative/dvc/images/5
-  :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/5
-  :alt: 5
+   :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/5
+   :alt: 5
 
 .. image:: https://sourcerer.io/fame/efiop/iterative/dvc/images/6
-  :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/6
-  :alt: 6
+   :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/6
+   :alt: 6
 
 .. image:: https://sourcerer.io/fame/efiop/iterative/dvc/images/7
-  :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/7
-  :alt: 7
+   :target: https://sourcerer.io/fame/efiop/iterative/dvc/links/7
+   :alt: 7
 
 Mailing List
 ============
@@ -253,3 +247,67 @@ This project is distributed under the Apache license version 2.0 (see the LICENS
 
 By submitting a pull request to this project, you agree to license your contribution under the Apache license version
 2.0 to this project.
+
+Citation
+========
+
+|DOI|
+
+Iterative, *DVC: Data Version Control - Git for Data & Models* (2020)
+`DOI:10.5281/zenodo.012345 <https://doi.org/10.5281/zenodo.3677553>`_.
+
+.. |Banner| image:: https://dvc.org/img/logo-github-readme.png
+   :target: https://dvc.org
+   :alt: DVC logo
+
+.. |Release| image:: https://img.shields.io/badge/release-ok-brightgreen
+   :target: https://travis-ci.com/iterative/dvc/branches
+   :alt: Release
+
+.. |CI| image:: https://img.shields.io/travis/com/iterative/dvc/master?label=dev&logo=travis
+   :target: https://travis-ci.com/iterative/dvc/builds
+   :alt: Travis dev branch
+
+.. |Maintainability| image:: https://codeclimate.com/github/iterative/dvc/badges/gpa.svg
+   :target: https://codeclimate.com/github/iterative/dvc
+   :alt: Code Climate
+
+.. |Coverage| image:: https://codecov.io/gh/iterative/dvc/branch/master/graph/badge.svg
+   :target: https://codecov.io/gh/iterative/dvc
+   :alt: Codecov
+
+.. |Donate| image:: https://img.shields.io/badge/patreon-donate-green.svg?logo=patreon
+   :target: https://www.patreon.com/DVCorg/overview
+   :alt: Donate
+
+.. |Snap| image:: https://img.shields.io/badge/snap-install-82BEA0.svg?logo=snapcraft
+   :target: https://snapcraft.io/dvc
+   :alt: Snapcraft
+
+.. |Choco| image:: https://img.shields.io/chocolatey/v/dvc?label=choco
+   :target: https://chocolatey.org/packages/dvc
+   :alt: Chocolatey
+
+.. |Brew| image:: https://img.shields.io/homebrew/v/dvc?label=brew
+   :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
+   :target: https://anaconda.org/conda-forge/dvc
+   :alt: Conda-forge
+
+.. |PyPI| image:: https://img.shields.io/pypi/v/dvc.svg?label=pip&logo=PyPI&logoColor=white
+   :target: https://pypi.org/project/dvc
+   :alt: PyPI
+
+.. |Packages| image:: https://img.shields.io/github/v/release/iterative/dvc?label=deb|pkg|rpm|exe&logo=GitHub
+   :target: https://github.com/iterative/dvc/releases/latest
+   :alt: deb|pkg|rpm|exe
+
+.. |DOI| image:: https://img.shields.io/badge/DOI-10.5281/zenodo.3677553-blue.svg
+   :target: https://doi.org/10.5281/zenodo.3677553
+   :alt: DOI
+
+.. |Flowchart| image:: https://dvc.org/img/flow.gif
+   :target: https://dvc.org/img/flow.gif
+   :alt: how_dvc_works

dvc/__init__.py

@@ -3,17 +3,7 @@ DVC
 ----
 Make your data science projects reproducible and shareable.
 """
-import warnings
-
 import dvc.logger
 from dvc.version import __version__  # noqa: F401
 
-
 dvc.logger.setup()
-
-# Ignore numpy's runtime warnings: https://github.com/numpy/numpy/pull/432.
-# We don't directly import numpy, but our dependency networkx does, causing
-# these warnings in some environments. Luckily these warnings are benign and
-# we can simply ignore them so that they don't show up when you are using dvc.
-warnings.filterwarnings("ignore", message="numpy.dtype size changed")
-warnings.filterwarnings("ignore", message="numpy.ufunc size changed")

dvc/analytics.py

@@ -2,12 +2,12 @@ import json
 import logging
 import os
 import platform
-import requests
 import sys
 import tempfile
 import uuid
 
 import distro
+import requests
 
 from dvc import __version__
 from dvc.config import Config, to_bool
@@ -15,11 +15,11 @@ from dvc.daemon import daemon
 from dvc.exceptions import NotDvcRepoError
 from dvc.lock import Lock, LockError
 from dvc.repo import Repo
-from dvc.scm import SCM
+from dvc.scm import SCM, NoSCM
+from dvc.scm.base import SCMError
 from dvc.utils import env2bool, is_binary
 from dvc.utils.fs import makedirs
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -35,7 +35,7 @@ def collect_and_send_report(args=None, return_code=None):
     report as a JSON, where the _collector_ generates it and the _sender_
     removes it after sending it.
     """
-    report = _runtime_info()
+    report = {}
 
     # Include command execution information on the report only when available.
     if args and hasattr(args, "func"):
@@ -61,7 +61,7 @@ def is_enabled():
     return enabled
 
 
-def send(report):
+def send(path):
     """
     Side effect: Removes the report after sending it.
 
@@ -72,19 +72,25 @@ def send(report):
     url = "https://analytics.dvc.org"
     headers = {"content-type": "application/json"}
 
-    with open(report, "rb") as fobj:
-        try:
-            requests.post(url, data=fobj, headers=headers, timeout=5)
-        except requests.exceptions.RequestException:
-            logger.debug("failed to send analytics report", exc_info=True)
+    with open(path) as fobj:
+        report = json.load(fobj)
 
-    os.remove(report)
+    report.update(_runtime_info())
+
+    try:
+        requests.post(url, json=report, headers=headers, timeout=5)
+    except requests.exceptions.RequestException:
+        logger.debug("failed to send analytics report", exc_info=True)
+
+    os.remove(path)
 
 
 def _scm_in_use():
     try:
         scm = SCM(root_dir=Repo.find_root())
         return type(scm).__name__
+    except SCMError:
+        return NoSCM.__name__
     except NotDvcRepoError:
         pass
 
@@ -152,7 +158,7 @@ def _find_or_create_user_id():
     try:
         with Lock(lockfile):
             try:
-                with open(fname, "r") as fobj:
+                with open(fname) as fobj:
                     user_id = json.load(fobj)["user_id"]
 
             except (FileNotFoundError, ValueError, KeyError):
@@ -164,6 +170,4 @@ def _find_or_create_user_id():
             return user_id
 
     except LockError:
-        logger.debug(
-            "Failed to acquire '{lockfile}'".format(lockfile=lockfile)
-        )
+        logger.debug(f"Failed to acquire '{lockfile}'")

dvc/api.py

@@ -1,37 +1,53 @@
 import os
-from contextlib import contextmanager, _GeneratorContextManager as GCM
+from contextlib import _GeneratorContextManager as GCM
+from contextlib import contextmanager
 
-from dvc.repo import Repo
 from dvc.exceptions import DvcException, NotDvcRepoError
 from dvc.external_repo import external_repo
+from dvc.repo import Repo
 
 
 class UrlNotDvcRepoError(DvcException):
-    """Thrown if given URL is not a DVC repository.
-
-    Args:
-        url (str): URL to the repository
-    """
+    """Thrown if the given URL is not a DVC repository."""
 
     def __init__(self, url):
-        super().__init__("'{}' is not a DVC repository.".format(url))
+        super().__init__(f"'{url}' is not a DVC repository.")
 
 
 def get_url(path, repo=None, rev=None, remote=None):
     """
-    Returns the full URL to the data artifact specified by its `path` in a
-    `repo`.
-    NOTE: There is no guarantee that the file actually exists in that location.
+    Returns the URL to the storage location of a data file or directory tracked
+    in a DVC repo. For Git repos, HEAD is used unless a rev argument is
+    supplied. The default remote is tried unless a remote argument is supplied.
+
+    Raises UrlNotDvcRepoError if repo is not a DVC project.
+
+    NOTE: This function does not check for the actual existence of the file or
+    directory in the remote storage.
     """
     with _make_repo(repo, rev=rev) as _repo:
-        _require_dvc(_repo)
+        if not isinstance(_repo, Repo):
+            raise UrlNotDvcRepoError(_repo.url)  # pylint: disable=no-member
         out = _repo.find_out_by_relpath(path)
         remote_obj = _repo.cloud.get_remote(remote)
-        return str(remote_obj.checksum_to_path_info(out.checksum))
+        return str(remote_obj.hash_to_path_info(out.checksum))
 
 
-def open(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
-    """Context manager to open a file artifact as a file object."""
+def open(  # noqa, pylint: disable=redefined-builtin
+    path, repo=None, rev=None, remote=None, mode="r", encoding=None
+):
+    """
+    Open file in the supplied path tracked in a repo (both DVC projects and
+    plain Git repos are supported). For Git repos, HEAD is used unless a rev
+    argument is supplied. The default remote is tried unless a remote argument
+    is supplied. It may only be used as a context manager:
+
+        with dvc.api.open(
+                'path/to/file',
+                repo='https://example.com/url/to/repo'
+                ) as fd:
+            # ... Handle file object fd
+    """
     args = (path,)
     kwargs = {
         "repo": repo,
@@ -44,7 +60,9 @@ def open(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
 
 
 class _OpenContextManager(GCM):
-    def __init__(self, func, args, kwds):
+    def __init__(
+        self, func, args, kwds
+    ):  # pylint: disable=super-init-not-called
         self.gen = func(*args, **kwds)
         self.func, self.args, self.kwds = func, args, kwds
 
@@ -63,7 +81,11 @@ def _open(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
 
 
 def read(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
-    """Returns the contents of a file artifact."""
+    """
+    Returns the contents of a tracked file (by DVC or Git). For Git repos, HEAD
+    is used unless a rev argument is supplied. The default remote is tried
+    unless a remote argument is supplied.
+    """
     with open(
         path, repo=repo, rev=rev, remote=remote, mode=mode, encoding=encoding
     ) as fd:
@@ -81,8 +103,3 @@ def _make_repo(repo_url=None, rev=None):
             pass  # fallthrough to external_repo
     with external_repo(url=repo_url, rev=rev) as repo:
         yield repo
-
-
-def _require_dvc(repo):
-    if not isinstance(repo, Repo):
-        raise UrlNotDvcRepoError(repo.url)

dvc/cache.py

@@ -28,19 +28,21 @@ def _make_remote_property(name):
     """
 
     def getter(self):
-        from dvc.remote import Remote
+        from dvc.remote import get_cloud_tree
+        from dvc.remote.base import CloudCache
 
         remote = self.config.get(name)
         if not remote:
             return None
 
-        return Remote(self.repo, name=remote)
+        tree = get_cloud_tree(self.repo, name=remote)
+        return CloudCache(tree)
 
     getter.__name__ = name
     return cached_property(getter)
 
 
-class Cache(object):
+class Cache:
     """Class that manages cache locations of a DVC repo.
 
     Args:
@@ -50,7 +52,8 @@ class Cache(object):
     CACHE_DIR = "cache"
 
     def __init__(self, repo):
-        from dvc.remote import Remote
+        from dvc.remote import get_cloud_tree
+        from dvc.remote.local import LocalCache
 
         self.repo = repo
         self.config = config = repo.config["cache"]
@@ -62,7 +65,8 @@ class Cache(object):
         else:
             settings = {**config, "url": config["dir"]}
 
-        self.local = Remote(repo, **settings)
+        tree = get_cloud_tree(repo, **settings)
+        self.local = LocalCache(tree)
 
     s3 = _make_remote_property("s3")
     gs = _make_remote_property("gs")
@@ -71,9 +75,40 @@ class Cache(object):
     azure = _make_remote_property("azure")
 
 
-class NamedCache(object):
+class NamedCacheItem:
     def __init__(self):
-        self._items = defaultdict(lambda: defaultdict(set))
+        self.names = set()
+        self.children = defaultdict(NamedCacheItem)
+
+    def __eq__(self, other):
+        return self.names == other.names and self.children == other.children
+
+    def child_keys(self):
+        for key, child in self.children.items():
+            yield key
+            yield from child.child_keys()
+
+    def child_names(self):
+        for key, child in self.children.items():
+            yield key, child.names
+            yield from child.child_names()
+
+    def add(self, checksum, item):
+        self.children[checksum].update(item)
+
+    def update(self, item, suffix=""):
+        if suffix:
+            self.names.update(n + suffix for n in item.names)
+        else:
+            self.names.update(item.names)
+        for checksum, child_item in item.children.items():
+            self.children[checksum].update(child_item)
+
+
+class NamedCache:
+    # pylint: disable=protected-access
+    def __init__(self):
+        self._items = defaultdict(lambda: defaultdict(NamedCacheItem))
         self.external = defaultdict(set)
 
     @classmethod
@@ -86,7 +121,18 @@ class NamedCache(object):
         return self._items[key]
 
     def add(self, scheme, checksum, name):
-        self._items[scheme][checksum].add(name)
+        """Add a mapped name for the specified checksum."""
+        self._items[scheme][checksum].names.add(name)
+
+    def add_child_cache(self, checksum, cache, suffix=""):
+        """Add/update child cache for the specified checksum."""
+        for scheme, src in cache._items.items():
+            dst = self._items[scheme][checksum].children
+            for child_checksum, item in src.items():
+                dst[child_checksum].update(item, suffix=suffix)
+
+        for repo_pair, files in cache.external.items():
+            self.external[repo_pair].update(files)
 
     def add_external(self, url, rev, path):
         self.external[url, rev].add(path)
@@ -94,11 +140,32 @@ class NamedCache(object):
     def update(self, cache, suffix=""):
         for scheme, src in cache._items.items():
             dst = self._items[scheme]
-            for checksum, names in src.items():
-                if suffix:
-                    dst[checksum].update(n + suffix for n in names)
-                else:
-                    dst[checksum].update(names)
+            for checksum, item in src.items():
+                dst[checksum].update(item, suffix=suffix)
 
         for repo_pair, files in cache.external.items():
             self.external[repo_pair].update(files)
+
+    def scheme_keys(self, scheme):
+        """Iterate over a flat list of all keys for the specified scheme,
+        including children.
+        """
+        for key, item in self._items[scheme].items():
+            yield key
+            yield from item.child_keys()
+
+    def scheme_names(self, scheme):
+        """Iterate over a flat list of checksum, names items for the specified
+        scheme, including children.
+        """
+        for key, item in self._items[scheme].items():
+            yield key, item.names
+            yield from item.child_names()
+
+    def dir_keys(self, scheme):
+        return (
+            key for key, item in self._items[scheme].items() if item.children
+        )
+
+    def child_keys(self, scheme, checksum):
+        return self._items[scheme][checksum].child_keys()

dvc/cli.py

@@ -8,29 +8,32 @@ from .command import (
     cache,
     checkout,
     commit,
+    completion,
     config,
     daemon,
+    dag,
     data_sync,
     destroy,
     diff,
+    freeze,
     gc,
     get,
     get_url,
+    git_hook,
     imp,
     imp_url,
     init,
     install,
     ls,
-    lock,
     metrics,
     move,
-    pipeline,
+    params,
+    plots,
     remote,
     remove,
     repro,
     root,
     run,
-    tag,
     unprotect,
     update,
     version,
@@ -38,7 +41,6 @@ from .command import (
 from .command.base import fix_subparsers
 from .exceptions import DvcParserError
 
-
 logger = logging.getLogger(__name__)
 
 COMMANDS = [
@@ -61,35 +63,53 @@ COMMANDS = [
     remote,
     cache,
     metrics,
+    params,
     install,
     root,
     ls,
-    lock,
-    pipeline,
+    freeze,
+    dag,
     daemon,
     commit,
-    tag,
+    completion,
     diff,
     version,
     update,
+    git_hook,
+    plots,
 ]
 
 
 class DvcParser(argparse.ArgumentParser):
     """Custom parser class for dvc CLI."""
 
-    def error(self, message):
+    def error(self, message, command=None):  # pylint: disable=arguments-differ
         """Custom error method.
         Args:
             message (str): error message.
-
+            command (str): subcommand name for help message
         Raises:
             dvc.exceptions.DvcParser: dvc parser exception.
+
         """
         logger.error(message)
+        if command is not None:
+            for action in self._actions:
+                if action.dest == "cmd" and command in action.choices:
+                    subparser = action.choices[command]
+                    subparser.print_help()
+                    raise DvcParserError()
         self.print_help()
         raise DvcParserError()
 
+    # override this to send subcommand name to error method
+    def parse_args(self, args=None, namespace=None):
+        args, argv = self.parse_known_args(args, namespace)
+        if argv:
+            msg = "unrecognized arguments: %s"
+            self.error(msg % " ".join(argv), args.cmd)
+        return args
+
 
 class VersionAction(argparse.Action):  # pragma: no cover
     # pylint: disable=too-few-public-methods
@@ -113,28 +133,16 @@ def get_parent_parser():
 
     log_level_group = parent_parser.add_mutually_exclusive_group()
     log_level_group.add_argument(
-        "-q", "--quiet", action="store_true", default=False, help="Be quiet."
+        "-q", "--quiet", action="count", default=0, help="Be quiet."
     )
     log_level_group.add_argument(
-        "-v",
-        "--verbose",
-        action="store_true",
-        default=False,
-        help="Be verbose.",
+        "-v", "--verbose", action="count", default=0, help="Be verbose."
     )
 
     return parent_parser
 
 
-def parse_args(argv=None):
-    """Parses CLI arguments.
-
-    Args:
-        argv: optional list of arguments to parse. sys.argv is used by default.
-
-    Raises:
-        dvc.exceptions.DvcParserError: raised for argument parsing errors.
-    """
+def get_main_parser():
     parent_parser = get_parent_parser()
 
     # Main parser
@@ -182,6 +190,18 @@ def parse_args(argv=None):
     for cmd in COMMANDS:
         cmd.add_parser(subparsers, parent_parser)
 
-    args = parser.parse_args(argv)
+    return parser
 
+
+def parse_args(argv=None):
+    """Parses CLI arguments.
+
+    Args:
+        argv: optional list of arguments to parse. sys.argv is used by default.
+
+    Raises:
+        dvc.exceptions.DvcParserError: raised for argument parsing errors.
+    """
+    parser = get_main_parser()
+    args = parser.parse_args(argv)
     return args

dvc/command/add.py

@@ -1,7 +1,8 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link, CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException, RecursiveAddingWhileUsingFilename
 
 logger = logging.getLogger(__name__)
@@ -18,6 +19,7 @@ class CmdAdd(CmdBase):
                 recursive=self.args.recursive,
                 no_commit=self.args.no_commit,
                 fname=self.args.file,
+                external=self.args.external,
             )
 
         except DvcException:
@@ -50,11 +52,17 @@ def add_parser(subparsers, parent_parser):
         help="Don't put files/directories into cache.",
     )
     parser.add_argument(
-        "-f",
-        "--file",
-        help="Specify name of the DVC-file this command will generate.",
+        "--external",
+        action="store_true",
+        default=False,
+        help="Allow targets that are outside of the DVC repository.",
     )
     parser.add_argument(
-        "targets", nargs="+", help="Input files/directories to add."
+        "--file",
+        help="Specify name of the DVC-file this command will generate.",
+        metavar="<filename>",
     )
+    parser.add_argument(
+        "targets", nargs="+", help="Input files/directories to add.",
+    ).complete = completion.FILE
     parser.set_defaults(func=CmdAdd)

dvc/command/base.py

@@ -1,5 +1,5 @@
 import logging
-
+from abc import ABC, abstractmethod
 
 logger = logging.getLogger(__name__)
 
@@ -27,7 +27,7 @@ def append_doc_link(help_message, path):
     )
 
 
-class CmdBase(object):
+class CmdBase(ABC):
     def __init__(self, args):
         from dvc.repo import Repo
         from dvc.updater import Updater
@@ -36,23 +36,22 @@ class CmdBase(object):
         self.config = self.repo.config
         self.args = args
         hardlink_lock = self.config["core"].get("hardlink_lock", False)
-        updater = Updater(self.repo.dvc_dir, hardlink_lock=hardlink_lock)
+        updater = Updater(self.repo.tmp_dir, hardlink_lock=hardlink_lock)
         updater.check()
 
     @property
     def default_targets(self):
-        """Default targets for `dvc repro` and `dvc pipeline`."""
-        from dvc.stage import Stage
+        """Default targets for `dvc repro`."""
+        from dvc.dvcfile import PIPELINE_FILE
 
-        msg = "assuming default target '{}'.".format(Stage.STAGE_FILE)
-        logger.warning(msg)
-        return [Stage.STAGE_FILE]
+        logger.debug(f"assuming default target '{PIPELINE_FILE}'.")
+        return [PIPELINE_FILE]
 
-    # Abstract methods that have to be implemented by any inheritance class
+    @abstractmethod
     def run(self):
-        raise NotImplementedError
+        pass
 
 
 class CmdBaseNoRepo(CmdBase):
-    def __init__(self, args):
+    def __init__(self, args):  # pylint: disable=super-init-not-called
         self.args = args

dvc/command/cache.py

@@ -1,5 +1,6 @@
 import argparse
 
+from dvc.command import completion
 from dvc.command.base import append_doc_link, fix_subparsers
 from dvc.command.config import CmdConfig
 
@@ -55,5 +56,5 @@ def add_parser(subparsers, parent_parser):
         help="Path to cache directory. Relative paths are resolved relative "
         "to the current directory and saved to config relative to the "
         "config file location.",
-    )
+    ).complete = completion.DIR
     cache_dir_parser.set_defaults(func=CmdCacheDir)

dvc/command/checkout.py

@@ -1,18 +1,68 @@
 import argparse
+import logging
+import operator
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+import colorama
+
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
+from dvc.exceptions import CheckoutError
+from dvc.utils.humanize import get_summary
+
+logger = logging.getLogger(__name__)
+
+
+def log_changes(stats):
+    colors = [
+        ("modified", colorama.Fore.YELLOW,),
+        ("added", colorama.Fore.GREEN),
+        ("deleted", colorama.Fore.RED,),
+    ]
+
+    for state, color in colors:
+        entries = stats.get(state)
+
+        if not entries:
+            continue
+
+        for entry in entries:
+            logger.info(
+                "{color}{state}{nc}{spacing}{entry}".format(
+                    color=color,
+                    state=state[0].upper(),
+                    nc=colorama.Fore.RESET,
+                    spacing="\t",
+                    entry=entry,
+                )
+            )
 
 
 class CmdCheckout(CmdBase):
     def run(self):
-        self.repo.checkout(
-            targets=self.args.targets,
-            with_deps=self.args.with_deps,
-            force=self.args.force,
-            relink=self.args.relink,
-            recursive=self.args.recursive,
-        )
+        stats, exc = None, None
+        try:
+            stats = self.repo.checkout(
+                targets=self.args.targets,
+                with_deps=self.args.with_deps,
+                force=self.args.force,
+                relink=self.args.relink,
+                recursive=self.args.recursive,
+            )
+        except CheckoutError as _exc:
+            exc = _exc
+            stats = exc.stats
+
+        if self.args.summary:
+            default_message = "No changes."
+            msg = get_summary(
+                sorted(stats.items(), key=operator.itemgetter(0))
+            )
+            logger.info(msg or default_message)
+        else:
+            log_changes(stats)
+
+        if exc:
+            raise exc
         return 0
 
 
@@ -26,6 +76,12 @@ def add_parser(subparsers, parent_parser):
         help=CHECKOUT_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
+    checkout_parser.add_argument(
+        "--summary",
+        action="store_true",
+        default=False,
+        help="Show summary of the changes.",
+    )
     checkout_parser.add_argument(
         "-d",
         "--with-deps",
@@ -58,5 +114,5 @@ def add_parser(subparsers, parent_parser):
         nargs="*",
         help="DVC-files to checkout. Optional. "
         "(Finds all DVC-files in the workspace by default.)",
-    )
+    ).complete = completion.DVC_FILE
     checkout_parser.set_defaults(func=CmdCheckout)

dvc/command/commit.py

@@ -1,11 +1,10 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -68,5 +67,5 @@ def add_parser(subparsers, parent_parser):
         nargs="*",
         help="DVC-files to commit. Optional. "
         "(Finds all DVC-files in the workspace by default.)",
-    )
+    ).complete = completion.DVC_FILE
     commit_parser.set_defaults(func=CmdCommit)

dvc/command/completion.py

@@ -0,0 +1,57 @@
+import argparse
+import logging
+
+import shtab
+
+from dvc.command.base import CmdBaseNoRepo, append_doc_link
+
+logger = logging.getLogger(__name__)
+FILE = shtab.FILE
+DIR = shtab.DIRECTORY
+DVC_FILE = {
+    "bash": "_dvc_compgen_DVCFiles",
+    "zsh": "_files -g '(*?.dvc|Dvcfile|dvc.yaml)'",
+}
+PREAMBLE = {
+    "bash": """
+# $1=COMP_WORDS[1]
+_dvc_compgen_DVCFiles() {
+  compgen -d -S '/' -- $1  # recurse into subdirs
+  compgen -f -X '!*?.dvc' -- $1
+  compgen -f -X '!*Dvcfile' -- $1
+  compgen -f -X '!*dvc.yaml' -- $1
+}
+""",
+    "zsh": "",
+}
+
+
+class CmdCompletion(CmdBaseNoRepo):
+    def run(self):
+        from dvc.cli import get_main_parser
+
+        parser = get_main_parser()
+        shell = self.args.shell
+        script = shtab.complete(parser, shell=shell, preamble=PREAMBLE)
+        print(script)
+        return 0
+
+
+def add_parser(subparsers, parent_parser):
+    COMPLETION_HELP = "Generate shell tab completion."
+    COMPLETION_DESCRIPTION = "Prints out shell tab completion scripts."
+    completion_parser = subparsers.add_parser(
+        "completion",
+        parents=[parent_parser],
+        description=append_doc_link(COMPLETION_DESCRIPTION, "completion"),
+        help=COMPLETION_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    completion_parser.add_argument(
+        "-s",
+        "--shell",
+        help="Shell syntax for completions.",
+        default="bash",
+        choices=["bash", "zsh"],
+    )
+    completion_parser.set_defaults(func=CmdCompletion)

dvc/command/config.py

@@ -1,7 +1,7 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link, CmdBaseNoRepo
+from dvc.command.base import CmdBaseNoRepo, append_doc_link
 from dvc.config import Config, ConfigError
 
 logger = logging.getLogger(__name__)
@@ -50,21 +50,22 @@ class CmdConfig(CmdBaseNoRepo):
 
 
 parent_config_parser = argparse.ArgumentParser(add_help=False)
-parent_config_parser.add_argument(
+level_group = parent_config_parser.add_mutually_exclusive_group()
+level_group.add_argument(
     "--global",
     dest="level",
     action="store_const",
     const="global",
     help="Use global config.",
 )
-parent_config_parser.add_argument(
+level_group.add_argument(
     "--system",
     dest="level",
     action="store_const",
     const="system",
     help="Use system config.",
 )
-parent_config_parser.add_argument(
+level_group.add_argument(
     "--local",
     dest="level",
     action="store_const",

dvc/command/daemon.py

@@ -1,5 +1,5 @@
-from dvc.command.base import CmdBaseNoRepo
-from dvc.command.base import fix_subparsers
+from dvc.command import completion
+from dvc.command.base import CmdBaseNoRepo, fix_subparsers
 
 
 class CmdDaemonBase(CmdBaseNoRepo):
@@ -15,9 +15,10 @@ class CmdDaemonUpdater(CmdDaemonBase):
 
         root_dir = Repo.find_root()
         dvc_dir = os.path.join(root_dir, Repo.DVC_DIR)
+        tmp_dir = os.path.join(dvc_dir, "tmp")
         config = Config(dvc_dir, validate=False)
         hardlink_lock = config.get("core", {}).get("hardlink_lock", False)
-        updater = Updater(dvc_dir, hardlink_lock=hardlink_lock)
+        updater = Updater(tmp_dir, hardlink_lock=hardlink_lock)
         updater.fetch(detach=False)
 
         return 0
@@ -64,5 +65,7 @@ def add_parser(subparsers, parent_parser):
         description=DAEMON_ANALYTICS_HELP,
         help=DAEMON_ANALYTICS_HELP,
     )
-    daemon_analytics_parser.add_argument("target", help="Analytics file.")
+    daemon_analytics_parser.add_argument(
+        "target", help="Analytics file.",
+    ).complete = completion.FILE
     daemon_analytics_parser.set_defaults(func=CmdDaemonAnalytics)

dvc/command/dag.py

@@ -0,0 +1,115 @@
+import argparse
+import logging
+
+from dvc.command.base import CmdBase, append_doc_link
+from dvc.exceptions import DvcException
+
+logger = logging.getLogger(__name__)
+
+
+def _show_ascii(G):
+    from dvc.repo.graph import get_pipelines
+    from dvc.dagascii import draw
+
+    pipelines = get_pipelines(G)
+
+    ret = []
+    for pipeline in pipelines:
+        ret.append(draw(pipeline.nodes, pipeline.edges))
+
+    return "\n".join(ret)
+
+
+def _show_dot(G):
+    import io
+    from networkx.drawing.nx_pydot import write_dot
+
+    dot_file = io.StringIO()
+    write_dot(G, dot_file)
+    return dot_file.getvalue()
+
+
+def _build(G, target=None, full=False):
+    import networkx as nx
+    from dvc.repo.graph import get_pipeline, get_pipelines
+
+    if target:
+        H = get_pipeline(get_pipelines(G), target)
+        if not full:
+            descendants = nx.descendants(G, target)
+            descendants.add(target)
+            H.remove_nodes_from(set(G.nodes()) - descendants)
+    else:
+        H = G
+
+    def _relabel(stage):
+        return stage.addressing
+
+    return nx.relabel_nodes(H, _relabel, copy=False)
+
+
+class CmdDAG(CmdBase):
+    def run(self):
+        try:
+            target = None
+            if self.args.target:
+                stages = self.repo.collect(self.args.target)
+                if len(stages) > 1:
+                    logger.error(
+                        f"'{self.args.target}' contains more than one stage "
+                        "{stages}, please specify one stage"
+                    )
+                    return 1
+                target = stages[0]
+
+            G = _build(self.repo.graph, target=target, full=self.args.full,)
+
+            if self.args.dot:
+                logger.info(_show_dot(G))
+            else:
+                from dvc.utils.pager import pager
+
+                pager(_show_ascii(G))
+
+            return 0
+        except DvcException:
+            msg = "failed to show "
+            if self.args.target:
+                msg += f"a pipeline for '{target}'"
+            else:
+                msg += "pipelines"
+            logger.exception(msg)
+            return 1
+
+
+def add_parser(subparsers, parent_parser):
+    DAG_HELP = "Visualize DVC project DAG."
+    dag_parser = subparsers.add_parser(
+        "dag",
+        parents=[parent_parser],
+        description=append_doc_link(DAG_HELP, "dag"),
+        help=DAG_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    dag_parser.add_argument(
+        "--dot",
+        action="store_true",
+        default=False,
+        help="Print DAG with .dot format.",
+    )
+    dag_parser.add_argument(
+        "--full",
+        action="store_true",
+        default=False,
+        help=(
+            "Show full DAG that the target belongs too, instead of "
+            "showing DAG consisting only of ancestors."
+        ),
+    )
+    dag_parser.add_argument(
+        "target",
+        nargs="?",
+        help="Stage or output to show pipeline for (optional). "
+        "Finds all stages in the workspace by default.",
+    )
+    dag_parser.set_defaults(func=CmdDAG)

dvc/command/data_sync.py

@@ -1,38 +1,46 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
-from dvc.exceptions import DvcException
-
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
+from dvc.command.checkout import log_changes
+from dvc.exceptions import CheckoutError, DvcException
+from dvc.utils.humanize import get_summary
 
 logger = logging.getLogger(__name__)
 
 
 class CmdDataBase(CmdBase):
-    @classmethod
-    def check_up_to_date(cls, processed_files_count):
-        if processed_files_count == 0:
-            logger.info("Everything is up to date.")
+    def log_summary(self, stats):
+        default_msg = "Everything is up to date."
+        logger.info(get_summary(stats.items()) or default_msg)
 
 
 class CmdDataPull(CmdDataBase):
+    def log_summary(self, stats):
+        log_changes(stats)
+        super().log_summary(stats)
+
     def run(self):
         try:
-            processed_files_count = self.repo.pull(
+            stats = self.repo.pull(
                 targets=self.args.targets,
                 jobs=self.args.jobs,
                 remote=self.args.remote,
                 all_branches=self.args.all_branches,
                 all_tags=self.args.all_tags,
+                all_commits=self.args.all_commits,
                 with_deps=self.args.with_deps,
                 force=self.args.force,
                 recursive=self.args.recursive,
+                run_cache=self.args.run_cache,
             )
-        except DvcException:
+            self.log_summary(stats)
+        except (CheckoutError, DvcException) as exc:
+            self.log_summary(getattr(exc, "stats", {}))
             logger.exception("failed to pull data from the cloud")
             return 1
-        self.check_up_to_date(processed_files_count)
+
         return 0
 
 
@@ -45,13 +53,15 @@ class CmdDataPush(CmdDataBase):
                 remote=self.args.remote,
                 all_branches=self.args.all_branches,
                 all_tags=self.args.all_tags,
+                all_commits=self.args.all_commits,
                 with_deps=self.args.with_deps,
                 recursive=self.args.recursive,
+                run_cache=self.args.run_cache,
             )
+            self.log_summary({"pushed": processed_files_count})
         except DvcException:
             logger.exception("failed to push data to the cloud")
             return 1
-        self.check_up_to_date(processed_files_count)
         return 0
 
 
@@ -64,13 +74,15 @@ class CmdDataFetch(CmdDataBase):
                 remote=self.args.remote,
                 all_branches=self.args.all_branches,
                 all_tags=self.args.all_tags,
+                all_commits=self.args.all_commits,
                 with_deps=self.args.with_deps,
                 recursive=self.args.recursive,
+                run_cache=self.args.run_cache,
             )
+            self.log_summary({"fetched": processed_files_count})
         except DvcException:
             logger.exception("failed to fetch data from the cloud")
             return 1
-        self.check_up_to_date(processed_files_count)
         return 0
 
 
@@ -78,27 +90,31 @@ def shared_parent_parser():
     from dvc.cli import get_parent_parser
 
     # Parent parser used in pull/push/status
-    shared_parent_parser = argparse.ArgumentParser(
+    parent_parser = argparse.ArgumentParser(
         add_help=False, parents=[get_parent_parser()]
     )
-    shared_parent_parser.add_argument(
-        "-j", "--jobs", type=int, help="Number of jobs to run simultaneously."
+    parent_parser.add_argument(
+        "-j",
+        "--jobs",
+        type=int,
+        help="Number of jobs to run simultaneously.",
+        metavar="<number>",
     )
-    shared_parent_parser.add_argument(
+    parent_parser.add_argument(
         "targets",
         nargs="*",
         help="Limit command scope to these DVC-files. "
         "Using -R, directories to search DVC-files in can also be given.",
-    )
+    ).complete = completion.DVC_FILE
 
-    return shared_parent_parser
+    return parent_parser
 
 
 def add_parser(subparsers, _parent_parser):
     from dvc.command.status import CmdDataStatus
 
     # Pull
-    PULL_HELP = "Pull data files from a DVC remote storage."
+    PULL_HELP = "Download tracked files or directories from remote storage."
 
     pull_parser = subparsers.add_parser(
         "pull",
@@ -108,7 +124,7 @@ def add_parser(subparsers, _parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     pull_parser.add_argument(
-        "-r", "--remote", help="Remote repository to pull from."
+        "-r", "--remote", help="Remote storage to pull from", metavar="<name>",
     )
     pull_parser.add_argument(
         "-a",
@@ -124,6 +140,12 @@ def add_parser(subparsers, _parent_parser):
         default=False,
         help="Fetch cache for all tags.",
     )
+    pull_parser.add_argument(
+        "--all-commits",
+        action="store_true",
+        default=False,
+        help="Fetch cache for all commits.",
+    )
     pull_parser.add_argument(
         "-f",
         "--force",
@@ -145,11 +167,16 @@ def add_parser(subparsers, _parent_parser):
         default=False,
         help="Pull cache for subdirectories of the specified directory.",
     )
+    pull_parser.add_argument(
+        "--run-cache",
+        action="store_true",
+        default=False,
+        help="Fetch run history for all stages.",
+    )
     pull_parser.set_defaults(func=CmdDataPull)
 
     # Push
-    PUSH_HELP = "Uploads files or directories tracked by DVC"
-    " to remote storage."
+    PUSH_HELP = "Upload tracked files or directories to remote storage."
 
     push_parser = subparsers.add_parser(
         "push",
@@ -159,7 +186,7 @@ def add_parser(subparsers, _parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     push_parser.add_argument(
-        "-r", "--remote", help="Remote repository to push to."
+        "-r", "--remote", help="Remote storage to push to", metavar="<name>",
     )
     push_parser.add_argument(
         "-a",
@@ -175,6 +202,12 @@ def add_parser(subparsers, _parent_parser):
         default=False,
         help="Push cache for all tags.",
     )
+    push_parser.add_argument(
+        "--all-commits",
+        action="store_true",
+        default=False,
+        help="Push cache for all commits.",
+    )
     push_parser.add_argument(
         "-d",
         "--with-deps",
@@ -187,13 +220,21 @@ def add_parser(subparsers, _parent_parser):
         "--recursive",
         action="store_true",
         default=False,
-        help="Push cache from subdirectories of specified directory.",
+        help="Push cache for subdirectories of specified directory.",
+    )
+    push_parser.add_argument(
+        "--run-cache",
+        action="store_true",
+        default=False,
+        help="Push run history for all stages.",
     )
     push_parser.set_defaults(func=CmdDataPush)
 
     # Fetch
-    FETCH_HELP = "Get files or directories tracked by DVC from remote storage"
-    " into the cache."
+    FETCH_HELP = (
+        "Get tracked files or directories from remote storage"
+        " into the cache."
+    )
 
     fetch_parser = subparsers.add_parser(
         "fetch",
@@ -203,7 +244,10 @@ def add_parser(subparsers, _parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     fetch_parser.add_argument(
-        "-r", "--remote", help="Remote repository to fetch from."
+        "-r",
+        "--remote",
+        help="Remote storage to fetch from",
+        metavar="<name>",
     )
     fetch_parser.add_argument(
         "-a",
@@ -219,6 +263,12 @@ def add_parser(subparsers, _parent_parser):
         default=False,
         help="Fetch cache for all tags.",
     )
+    fetch_parser.add_argument(
+        "--all-commits",
+        action="store_true",
+        default=False,
+        help="Fetch cache for all commits.",
+    )
     fetch_parser.add_argument(
         "-d",
         "--with-deps",
@@ -233,6 +283,12 @@ def add_parser(subparsers, _parent_parser):
         default=False,
         help="Fetch cache for subdirectories of specified directory.",
     )
+    fetch_parser.add_argument(
+        "--run-cache",
+        action="store_true",
+        default=False,
+        help="Fetch run history for all stages.",
+    )
     fetch_parser.set_defaults(func=CmdDataFetch)
 
     # Status
@@ -266,7 +322,10 @@ def add_parser(subparsers, _parent_parser):
         help="Show status of a local cache compared to a remote repository.",
     )
     status_parser.add_argument(
-        "-r", "--remote", help="Remote repository to compare local cache to."
+        "-r",
+        "--remote",
+        help="Remote storage to compare local cache to",
+        metavar="<name>",
     )
     status_parser.add_argument(
         "-a",
@@ -284,6 +343,13 @@ def add_parser(subparsers, _parent_parser):
         help="Show status of a local cache compared to a remote repository "
         "for all tags.",
     )
+    status_parser.add_argument(
+        "--all-commits",
+        action="store_true",
+        default=False,
+        help="Show status of a local cache compared to a remote repository "
+        "for all commits.",
+    )
     status_parser.add_argument(
         "-d",
         "--with-deps",
@@ -291,4 +357,18 @@ def add_parser(subparsers, _parent_parser):
         default=False,
         help="Show status for all dependencies of the specified target.",
     )
+    status_parser.add_argument(
+        "-R",
+        "--recursive",
+        action="store_true",
+        default=False,
+        help="Show status of all stages in the specified directory.",
+    )
+    status_parser.add_argument(
+        "--show-json",
+        action="store_true",
+        default=False,
+        help="Show status in JSON format.",
+    )
+
     status_parser.set_defaults(func=CmdDataStatus)

dvc/command/destroy.py

@@ -2,11 +2,9 @@ import argparse
 import logging
 
 import dvc.prompt as prompt
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -27,7 +25,7 @@ class CmdDestroy(CmdBase):
                 )
 
             self.repo.destroy()
-        except Exception:
+        except Exception:  # noqa, pylint: disable=broad-except
             logger.exception("failed to destroy DVC")
             return 1
         return 0

dvc/command/diff.py

@@ -8,10 +8,24 @@ import colorama
 from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
+def _show_md(diff):
+    from dvc.utils.diff import table
+
+    rows = []
+    for status in ["added", "deleted", "modified"]:
+        entries = diff.get(status, [])
+        if not entries:
+            continue
+        paths = sorted(entry["path"] for entry in entries)
+        for path in paths:
+            rows.append([status, path])
+
+    return table(["Status", "Path"], rows, True)
+
+
 class CmdDiff(CmdBase):
     @staticmethod
     def _format(diff):
@@ -28,7 +42,7 @@ class CmdDiff(CmdBase):
                 dir/
                 dir/1
 
-        An example of a diff formatted when entries contain checksums:
+        An example of a diff formatted when entries contain hash:
 
             Added:
                 d3b07384 foo
@@ -42,7 +56,7 @@ class CmdDiff(CmdBase):
         """
 
         def _digest(checksum):
-            if type(checksum) is str:
+            if isinstance(checksum, str):
                 return checksum[0:8]
             return "{}..{}".format(checksum["old"][0:8], checksum["new"][0:8])
 
@@ -66,7 +80,7 @@ class CmdDiff(CmdBase):
 
             for entry in entries:
                 path = entry["path"]
-                checksum = entry.get("checksum")
+                checksum = entry.get("hash")
                 summary[state] += 1 if not path.endswith(os.sep) else 0
                 content.append(
                     "{space}{checksum}{separator}{path}".format(
@@ -97,20 +111,17 @@ class CmdDiff(CmdBase):
         try:
             diff = self.repo.diff(self.args.a_rev, self.args.b_rev)
 
-            if not any(diff.values()):
-                return 0
-
-            if not self.args.checksums:
+            if not self.args.show_hash:
                 for _, entries in diff.items():
                     for entry in entries:
-                        del entry["checksum"]
+                        del entry["hash"]
 
             if self.args.show_json:
-                res = json.dumps(diff)
-            else:
-                res = self._format(diff)
-
-            logger.info(res)
+                logger.info(json.dumps(diff))
+            elif self.args.show_md:
+                logger.info(_show_md(diff))
+            elif diff:
+                logger.info(self._format(diff))
 
         except DvcException:
             logger.exception("failed to get diff")
@@ -120,9 +131,8 @@ class CmdDiff(CmdBase):
 
 def add_parser(subparsers, parent_parser):
     DIFF_DESCRIPTION = (
-        "Show changes between commits in the DVC repository,"
-        " or between a commit and the workspace."
-        "Prints the list of paths added, modified, or deleted."
+        "Show added, modified, or deleted data between commits in the DVC"
+        " repository, or between a commit and the workspace."
     )
     diff_parser = subparsers.add_parser(
         "diff",
@@ -149,9 +159,15 @@ def add_parser(subparsers, parent_parser):
         default=False,
     )
     diff_parser.add_argument(
-        "--checksums",
+        "--show-hash",
         help="Display hash value for each entry",
         action="store_true",
         default=False,
     )
+    diff_parser.add_argument(
+        "--show-md",
+        help="Show tabulated output in the Markdown format (GFM).",
+        action="store_true",
+        default=False,
+    )
     diff_parser.set_defaults(func=CmdDiff)

dvc/command/freeze.py

@@ -0,0 +1,58 @@
+import argparse
+import logging
+
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
+from dvc.exceptions import DvcException
+
+logger = logging.getLogger(__name__)
+
+
+class CmdFreezeBase(CmdBase):
+    def _run(self, func, name):
+        ret = 0
+        for target in self.args.targets:
+            try:
+                func(target)
+            except DvcException:
+                logger.exception(f"failed to {name} '{target}'")
+                ret = 1
+        return ret
+
+
+class CmdFreeze(CmdFreezeBase):
+    def run(self):
+        return self._run(self.repo.freeze, "freeze")
+
+
+class CmdUnfreeze(CmdFreezeBase):
+    def run(self):
+        return self._run(self.repo.unfreeze, "unfreeze")
+
+
+def add_parser(subparsers, parent_parser):
+    FREEZE_HELP = "Freeze stages or .dvc files."
+    freeze_parser = subparsers.add_parser(
+        "freeze",
+        parents=[parent_parser],
+        description=append_doc_link(FREEZE_HELP, "freeze"),
+        help=FREEZE_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    freeze_parser.add_argument(
+        "targets", nargs="+", help="Stages or .dvc files to freeze",
+    ).complete = completion.DVC_FILE
+    freeze_parser.set_defaults(func=CmdFreeze)
+
+    UNFREEZE_HELP = "Unfreeze stages or .dvc files."
+    unfreeze_parser = subparsers.add_parser(
+        "unfreeze",
+        parents=[parent_parser],
+        description=append_doc_link(UNFREEZE_HELP, "unfreeze"),
+        help=UNFREEZE_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    unfreeze_parser.add_argument(
+        "targets", nargs="+", help="Stages or .dvc files to unfreeze",
+    ).complete = completion.DVC_FILE
+    unfreeze_parser.set_defaults(func=CmdUnfreeze)

dvc/command/gc.py

@@ -3,18 +3,25 @@ import logging
 import os
 
 import dvc.prompt as prompt
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
-
+from dvc.command.base import CmdBase, append_doc_link
 
 logger = logging.getLogger(__name__)
 
 
 class CmdGC(CmdBase):
     def run(self):
+        from dvc.repo.gc import _raise_error_if_all_disabled
+
+        _raise_error_if_all_disabled(
+            all_branches=self.args.all_branches,
+            all_tags=self.args.all_tags,
+            all_commits=self.args.all_commits,
+            workspace=self.args.workspace,
+        )
+
         msg = "This will remove all cache except items used in "
 
-        msg += "the working tree"
+        msg += "the workspace"
         if self.args.all_commits:
             msg += " and all git commits"
         elif self.args.all_branches and self.args.all_tags:
@@ -47,6 +54,7 @@ class CmdGC(CmdBase):
             force=self.args.force,
             jobs=self.args.jobs,
             repos=self.args.repos,
+            workspace=self.args.workspace,
         )
         return 0
 
@@ -64,25 +72,32 @@ def add_parser(subparsers, parent_parser):
         help=GC_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
+    gc_parser.add_argument(
+        "-w",
+        "--workspace",
+        action="store_true",
+        default=False,
+        help="Keep data files used in the current workspace.",
+    )
     gc_parser.add_argument(
         "-a",
         "--all-branches",
         action="store_true",
         default=False,
-        help="Keep data files for the tips of all git branches.",
+        help="Keep data files for the tips of all Git branches.",
     )
     gc_parser.add_argument(
         "-T",
         "--all-tags",
         action="store_true",
         default=False,
-        help="Keep data files for all git tags.",
+        help="Keep data files for all Git tags.",
     )
     gc_parser.add_argument(
         "--all-commits",
         action="store_true",
         default=False,
-        help=argparse.SUPPRESS,
+        help="Keep data files for all Git commits.",
     )
     gc_parser.add_argument(
         "-c",
@@ -92,7 +107,10 @@ def add_parser(subparsers, parent_parser):
         help="Collect garbage in remote repository.",
     )
     gc_parser.add_argument(
-        "-r", "--remote", help="Remote storage to collect garbage in."
+        "-r",
+        "--remote",
+        help="Remote storage to collect garbage in",
+        metavar="<name>",
     )
     gc_parser.add_argument(
         "-f",
@@ -102,7 +120,11 @@ def add_parser(subparsers, parent_parser):
         help="Force garbage collection - automatically agree to all prompts.",
     )
     gc_parser.add_argument(
-        "-j", "--jobs", type=int, help="Number of jobs to run simultaneously."
+        "-j",
+        "--jobs",
+        type=int,
+        help="Number of jobs to run simultaneously.",
+        metavar="<number>",
     )
     gc_parser.add_argument(
         "-p",
@@ -113,5 +135,6 @@ def add_parser(subparsers, parent_parser):
         help="Keep data files required by these projects "
         "in addition to the current one. "
         "Useful if you share a single cache across repos.",
+        metavar="<paths>",
     )
     gc_parser.set_defaults(func=CmdGC)

dvc/command/get.py

@@ -1,10 +1,10 @@
 import argparse
 import logging
 
-from .base import append_doc_link
-from .base import CmdBaseNoRepo
 from dvc.exceptions import DvcException
 
+from . import completion
+from .base import CmdBaseNoRepo, append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -63,13 +63,20 @@ def add_parser(subparsers, parent_parser):
         "url", help="Location of DVC or Git repository to download from"
     )
     get_parser.add_argument(
-        "path", help="Path to a file or directory within the repository"
-    )
+        "path", help="Path to a file or directory within the repository",
+    ).complete = completion.FILE
     get_parser.add_argument(
-        "-o", "--out", nargs="?", help="Destination path to download files to"
-    )
+        "-o",
+        "--out",
+        nargs="?",
+        help="Destination path to download files to",
+        metavar="<path>",
+    ).complete = completion.DIR
     get_parser.add_argument(
-        "--rev", nargs="?", help="Git revision (e.g. SHA, branch, tag)"
+        "--rev",
+        nargs="?",
+        help="Git revision (e.g. SHA, branch, tag)",
+        metavar="<commit>",
     )
     get_parser.add_argument(
         "--show-url",

dvc/command/get_url.py

@@ -1,10 +1,10 @@
 import argparse
 import logging
 
-from .base import append_doc_link
-from .base import CmdBaseNoRepo
 from dvc.exceptions import DvcException
 
+from . import completion
+from .base import CmdBaseNoRepo, append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -17,7 +17,7 @@ class CmdGetUrl(CmdBaseNoRepo):
             Repo.get_url(self.args.url, out=self.args.out)
             return 0
         except DvcException:
-            logger.exception("failed to get '{}'".format(self.args.url))
+            logger.exception(f"failed to get '{self.args.url}'")
             return 1
 
 
@@ -34,6 +34,6 @@ def add_parser(subparsers, parent_parser):
         "url", help="See `dvc import-url -h` for full list of supported URLs."
     )
     get_parser.add_argument(
-        "out", nargs="?", help="Destination path to put data to."
-    )
+        "out", nargs="?", help="Destination path to put data to.",
+    ).complete = completion.DIR
     get_parser.set_defaults(func=CmdGetUrl)

dvc/command/git_hook.py

@@ -0,0 +1,115 @@
+import logging
+import os
+
+from dvc.command.base import CmdBaseNoRepo, fix_subparsers
+from dvc.exceptions import NotDvcRepoError
+
+logger = logging.getLogger(__name__)
+
+
+class CmdHookBase(CmdBaseNoRepo):
+    def run(self):
+        from dvc.repo import Repo
+
+        try:
+            repo = Repo()
+            repo.close()
+        except NotDvcRepoError:
+            return 0
+
+        return self._run()
+
+    def _run(self):
+        raise NotImplementedError
+
+
+class CmdPreCommit(CmdHookBase):
+    def _run(self):
+        from dvc.main import main
+
+        return main(["status"])
+
+
+class CmdPostCheckout(CmdHookBase):
+    def _run(self):
+        # when we are running from pre-commit tool, it doesn't provide CLI
+        # flags, but instead provides respective env vars that we could use.
+        flag = os.environ.get("PRE_COMMIT_CHECKOUT_TYPE")
+        if flag is None and len(self.args.args) >= 3:
+            # see https://git-scm.com/docs/githooks#_post_checkout
+            flag = self.args.args[2]
+
+        # checking out some reference and not specific file.
+        if flag != "1":
+            return 0
+
+        # make sure we are not in the middle of a rebase/merge, so we
+        # don't accidentally break it with an unsuccessful checkout.
+        # Note that git hooks are always running in repo root.
+        if os.path.isdir(os.path.join(".git", "rebase-merge")):
+            return 0
+
+        from dvc.main import main
+
+        return main(["checkout"])
+
+
+class CmdPrePush(CmdHookBase):
+    def _run(self):
+        from dvc.main import main
+
+        return main(["push"])
+
+
+def add_parser(subparsers, parent_parser):
+    GIT_HOOK_HELP = "Run GIT hook."
+
+    git_hook_parser = subparsers.add_parser(
+        "git-hook",
+        parents=[parent_parser],
+        description=GIT_HOOK_HELP,
+        add_help=False,
+    )
+
+    git_hook_subparsers = git_hook_parser.add_subparsers(
+        dest="cmd",
+        help="Use `dvc daemon CMD --help` for command-specific help.",
+    )
+
+    fix_subparsers(git_hook_subparsers)
+
+    PRE_COMMIT_HELP = "Run pre-commit GIT hook."
+    pre_commit_parser = git_hook_subparsers.add_parser(
+        "pre-commit",
+        parents=[parent_parser],
+        description=PRE_COMMIT_HELP,
+        help=PRE_COMMIT_HELP,
+    )
+    pre_commit_parser.add_argument(
+        "args", nargs="*", help="Arguments passed by GIT or pre-commit tool.",
+    )
+    pre_commit_parser.set_defaults(func=CmdPreCommit)
+
+    POST_CHECKOUT_HELP = "Run post-checkout GIT hook."
+    post_checkout_parser = git_hook_subparsers.add_parser(
+        "post-checkout",
+        parents=[parent_parser],
+        description=POST_CHECKOUT_HELP,
+        help=POST_CHECKOUT_HELP,
+    )
+    post_checkout_parser.add_argument(
+        "args", nargs="*", help="Arguments passed by GIT or pre-commit tool.",
+    )
+    post_checkout_parser.set_defaults(func=CmdPostCheckout)
+
+    PRE_PUSH_HELP = "Run pre-push GIT hook."
+    pre_push_parser = git_hook_subparsers.add_parser(
+        "pre-push",
+        parents=[parent_parser],
+        description=PRE_PUSH_HELP,
+        help=PRE_PUSH_HELP,
+    )
+    pre_push_parser.add_argument(
+        "args", nargs="*", help="Arguments passed by GIT or pre-commit tool.",
+    )
+    pre_push_parser.set_defaults(func=CmdPrePush)

dvc/command/imp.py

@@ -1,11 +1,10 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -45,12 +44,19 @@ def add_parser(subparsers, parent_parser):
         "url", help="Location of DVC or Git repository to download from"
     )
     import_parser.add_argument(
-        "path", help="Path to a file or directory within the repository"
-    )
+        "path", help="Path to a file or directory within the repository",
+    ).complete = completion.FILE
     import_parser.add_argument(
-        "-o", "--out", nargs="?", help="Destination path to download files to"
-    )
+        "-o",
+        "--out",
+        nargs="?",
+        help="Destination path to download files to",
+        metavar="<path>",
+    ).complete = completion.DIR
     import_parser.add_argument(
-        "--rev", nargs="?", help="Git revision (e.g. SHA, branch, tag)"
+        "--rev",
+        nargs="?",
+        help="Git revision (e.g. SHA, branch, tag)",
+        metavar="<commit>",
     )
     import_parser.set_defaults(func=CmdImport)

dvc/command/imp_url.py

@@ -1,11 +1,10 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -13,7 +12,10 @@ class CmdImportUrl(CmdBase):
     def run(self):
         try:
             self.repo.imp_url(
-                self.args.url, out=self.args.out, fname=self.args.file
+                self.args.url,
+                out=self.args.out,
+                fname=self.args.file,
+                no_exec=self.args.no_exec,
             )
         except DvcException:
             logger.exception(
@@ -56,9 +58,17 @@ def add_parser(subparsers, parent_parser):
         "remote://myremote/path/to/file (see `dvc remote`)",
     )
     import_parser.add_argument(
-        "out", nargs="?", help="Destination path to put files to."
-    )
+        "out", nargs="?", help="Destination path to put files to.",
+    ).complete = completion.DIR
     import_parser.add_argument(
-        "-f", "--file", help="Specify name of the DVC-file it generates."
+        "--file",
+        help="Specify name of the DVC-file this command will generate.",
+        metavar="<filename>",
+    ).complete = completion.DIR
+    import_parser.add_argument(
+        "--no-exec",
+        action="store_true",
+        default=False,
+        help="Only create DVC-file without actually downloading it.",
     )
     import_parser.set_defaults(func=CmdImportUrl)

dvc/command/init.py

@@ -1,9 +1,7 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBaseNoRepo
-
+from dvc.command.base import CmdBaseNoRepo, append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -15,7 +13,10 @@ class CmdInit(CmdBaseNoRepo):
 
         try:
             self.repo = Repo.init(
-                ".", no_scm=self.args.no_scm, force=self.args.force
+                ".",
+                no_scm=self.args.no_scm,
+                force=self.args.force,
+                subdir=self.args.subdir,
             )
             self.config = self.repo.config
         except InitError:
@@ -44,7 +45,7 @@ def add_parser(subparsers, parent_parser):
         action="store_true",
         default=False,
         help="Initiate DVC in directory that is "
-        "not tracked by any scm tool (e.g. git).",
+        "not tracked by any SCM tool (e.g. Git).",
     )
     init_parser.add_argument(
         "-f",
@@ -56,4 +57,13 @@ def add_parser(subparsers, parent_parser):
             "This operation removes local cache."
         ),
     )
+    init_parser.add_argument(
+        "--subdir",
+        action="store_true",
+        default=False,
+        help=(
+            "Necessary for running this command inside a subdirectory of a "
+            "parent SCM repository."
+        ),
+    )
     init_parser.set_defaults(func=CmdInit)

dvc/command/install.py

@@ -1,9 +1,7 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
-
+from dvc.command.base import CmdBase, append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -11,8 +9,8 @@ logger = logging.getLogger(__name__)
 class CmdInstall(CmdBase):
     def run(self):
         try:
-            self.repo.install()
-        except Exception:
+            self.repo.install(self.args.use_pre_commit_tool)
+        except Exception:  # noqa, pylint:disable=broad-except
             logger.exception("failed to install DVC Git hooks")
             return 1
         return 0
@@ -27,4 +25,11 @@ def add_parser(subparsers, parent_parser):
         help=INSTALL_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
+    install_parser.add_argument(
+        "--use-pre-commit-tool",
+        action="store_true",
+        default=False,
+        help="Install DVC hooks using pre-commit "
+        "(https://pre-commit.com) if it is installed.",
+    )
     install_parser.set_defaults(func=CmdInstall)

dvc/command/lock.py

@@ -1,61 +0,0 @@
-import argparse
-import logging
-
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
-from dvc.exceptions import DvcException
-
-
-logger = logging.getLogger(__name__)
-
-
-class CmdLockBase(CmdBase):
-    def _run(self, unlock):
-        for target in self.args.targets:
-            try:
-                self.repo.lock_stage(target, unlock=unlock)
-            except DvcException:
-                logger.exception(
-                    "failed to {}lock '{}'".format(
-                        "un" if unlock else "", target
-                    )
-                )
-
-                return 1
-        return 0
-
-
-class CmdLock(CmdLockBase):
-    def run(self):
-        return self._run(False)
-
-
-class CmdUnlock(CmdLockBase):
-    def run(self):
-        return self._run(True)
-
-
-def add_parser(subparsers, parent_parser):
-    LOCK_HELP = "Lock DVC-files."
-    lock_parser = subparsers.add_parser(
-        "lock",
-        parents=[parent_parser],
-        description=append_doc_link(LOCK_HELP, "lock"),
-        help=LOCK_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    lock_parser.add_argument("targets", nargs="+", help="DVC-files to lock.")
-    lock_parser.set_defaults(func=CmdLock)
-
-    UNLOCK_HELP = "Unlock DVC-files."
-    unlock_parser = subparsers.add_parser(
-        "unlock",
-        parents=[parent_parser],
-        description=append_doc_link(UNLOCK_HELP, "unlock"),
-        help=UNLOCK_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    unlock_parser.add_argument(
-        "targets", nargs="+", help="DVC-files to unlock."
-    )
-    unlock_parser.set_defaults(func=CmdUnlock)

dvc/command/ls.py

@@ -1,68 +0,0 @@
-import argparse
-import logging
-
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBaseNoRepo
-from dvc.exceptions import DvcException
-
-
-logger = logging.getLogger(__name__)
-
-
-class CmdList(CmdBaseNoRepo):
-    def run(self):
-        from dvc.repo import Repo
-
-        try:
-            nodes = Repo.ls(
-                self.args.url,
-                self.args.target,
-                rev=self.args.rev,
-                recursive=self.args.recursive,
-                outs_only=self.args.outs_only,
-            )
-            if nodes:
-                logger.info("\n".join(nodes))
-            return 0
-        except DvcException:
-            logger.exception("failed to list '{}'".format(self.args.url))
-            return 1
-
-
-def add_parser(subparsers, parent_parser):
-    LIST_HELP = "List files and DVC outputs in the repo."
-    list_parser = subparsers.add_parser(
-        "list",
-        parents=[parent_parser],
-        description=append_doc_link(LIST_HELP, "list"),
-        help=LIST_HELP,
-        formatter_class=argparse.RawTextHelpFormatter,
-    )
-    list_parser.add_argument(
-        "url",
-        help="Supported urls:\n"
-        "/path/to/file\n"
-        "/path/to/directory\n"
-        "C:\\\\path\\to\\file\n"
-        "C:\\\\path\\to\\directory\n"
-        "https://github.com/path/to/repo\n"
-        "[email protected]:path/to/repo.git\n",
-    )
-    list_parser.add_argument(
-        "-R",
-        "--recursive",
-        action="store_true",
-        help="Recursively list files.",
-    )
-    list_parser.add_argument(
-        "--outs-only", action="store_true", help="Show only DVC outputs."
-    )
-    list_parser.add_argument(
-        "--rev", nargs="?", help="Git revision (e.g. branch, tag, SHA)"
-    )
-    list_parser.add_argument(
-        "target",
-        nargs="?",
-        help="Path to directory within the repository to list outputs for",
-    )
-    list_parser.set_defaults(func=CmdList)

dvc/command/ls/__init__.py

@@ -0,0 +1,79 @@
+import argparse
+import logging
+import sys
+
+from dvc.command import completion
+from dvc.command.base import CmdBaseNoRepo, append_doc_link
+from dvc.command.ls.ls_colors import LsColors
+from dvc.exceptions import DvcException
+
+logger = logging.getLogger(__name__)
+
+
+def _prettify(entries, with_color=False):
+    if with_color:
+        ls_colors = LsColors()
+        fmt = ls_colors.format
+    else:
+
+        def fmt(entry):
+            return entry["path"]
+
+    return [fmt(entry) for entry in entries]
+
+
+class CmdList(CmdBaseNoRepo):
+    def run(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,
+            )
+            if entries:
+                entries = _prettify(entries, sys.stdout.isatty())
+                logger.info("\n".join(entries))
+            return 0
+        except DvcException:
+            logger.exception(f"failed to list '{self.args.url}'")
+            return 1
+
+
+def add_parser(subparsers, parent_parser):
+    LIST_HELP = (
+        "List repository contents, including files"
+        " and directories tracked by DVC and by Git."
+    )
+    list_parser = subparsers.add_parser(
+        "list",
+        parents=[parent_parser],
+        description=append_doc_link(LIST_HELP, "list"),
+        help=LIST_HELP,
+        formatter_class=argparse.RawTextHelpFormatter,
+    )
+    list_parser.add_argument("url", help="Location of DVC repository to list")
+    list_parser.add_argument(
+        "-R",
+        "--recursive",
+        action="store_true",
+        help="Recursively list files.",
+    )
+    list_parser.add_argument(
+        "--dvc-only", action="store_true", help="Show only DVC outputs."
+    )
+    list_parser.add_argument(
+        "--rev",
+        nargs="?",
+        help="Git revision (e.g. SHA, branch, tag)",
+        metavar="<commit>",
+    )
+    list_parser.add_argument(
+        "path",
+        nargs="?",
+        help="Path to directory within the repository to list outputs for",
+    ).complete = completion.DIR
+    list_parser.set_defaults(func=CmdList)

dvc/command/ls/ls_colors.py

@@ -0,0 +1,48 @@
+import os
+
+
+class LsColors:
+    default = "rs=0:di=01;34:ex=01;32"
+
+    def __init__(self, lscolors=None):
+        self._extensions = {}
+        self._codes = {}
+        self._load(lscolors or os.environ.get("LS_COLORS") or LsColors.default)
+
+    def _load(self, lscolors):
+        for item in lscolors.split(":"):
+            try:
+                code, color = item.split("=", 1)
+            except ValueError:
+                continue
+            if code.startswith("*."):
+                self._extensions[code[1:]] = color
+            else:
+                self._codes[code] = color
+
+    def format(self, entry):
+        text = entry["path"]
+
+        if entry.get("isout", False) and "out" in self._codes:
+            return self._format(text, code="out")
+
+        if entry.get("isdir", False):
+            return self._format(text, code="di")
+
+        if entry.get("isexec", False):
+            return self._format(text, code="ex")
+
+        _, ext = os.path.splitext(text)
+        return self._format(text, ext=ext)
+
+    def _format(self, text, code=None, ext=None):
+        val = None
+        if ext:
+            val = self._extensions.get(ext, None)
+        if code:
+            val = self._codes.get(code, None)
+
+        if not val:
+            return text
+        rs = self._codes.get("rs", 0)
+        return f"\033[{val}m{text}\033[{rs}m"

dvc/command/metrics.py

@@ -1,46 +1,38 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
-from dvc.command.base import fix_subparsers
-from dvc.exceptions import BadMetricError
-from dvc.exceptions import DvcException
-
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
+from dvc.exceptions import BadMetricError, DvcException
 
 logger = logging.getLogger(__name__)
 
 
-def show_metrics(metrics, all_branches=False, all_tags=False):
-    """
-    Args:
-        metrics (list): Where each element is either a `list`
-            if an xpath was specified, otherwise a `str`
-    """
+DEFAULT_PRECISION = 5
+
+
+def show_metrics(
+    metrics, all_branches=False, all_tags=False, all_commits=False
+):
+    from flatten_json import flatten
+    from dvc.utils.diff import format_dict
+
     # When `metrics` contains a `None` key, it means that some files
     # specified as `targets` in `repo.metrics.show` didn't contain any metrics.
     missing = metrics.pop(None, None)
 
     for branch, val in metrics.items():
-        if all_branches or all_tags:
-            logger.info("{branch}:".format(branch=branch))
+        if all_branches or all_tags or all_commits:
+            logger.info(f"{branch}:")
 
         for fname, metric in val.items():
-            if isinstance(metric, dict):
-                lines = list(metric.values())
-            elif isinstance(metric, list):
-                lines = metric
-            else:
-                lines = metric.splitlines()
+            if not isinstance(metric, dict):
+                logger.info("\t{}: {}".format(fname, str(metric)))
+                continue
 
-            if len(lines) > 1:
-                logger.info("\t{fname}:".format(fname=fname))
-
-                for line in lines:
-                    logger.info("\t\t{content}".format(content=line))
-
-            else:
-                logger.info("\t{}: {}".format(fname, metric))
+            logger.info(f"\t{fname}:")
+            for key, value in flatten(format_dict(metric), ".").items():
+                logger.info(f"\t\t{key}: {value}")
 
     if missing:
         raise BadMetricError(missing)
@@ -51,14 +43,23 @@ class CmdMetricsShow(CmdBase):
         try:
             metrics = self.repo.metrics.show(
                 self.args.targets,
-                typ=self.args.type,
-                xpath=self.args.xpath,
                 all_branches=self.args.all_branches,
                 all_tags=self.args.all_tags,
+                all_commits=self.args.all_commits,
                 recursive=self.args.recursive,
             )
 
-            show_metrics(metrics, self.args.all_branches, self.args.all_tags)
+            if self.args.show_json:
+                import json
+
+                logger.info(json.dumps(metrics))
+            else:
+                show_metrics(
+                    metrics,
+                    self.args.all_branches,
+                    self.args.all_tags,
+                    self.args.all_commits,
+                )
         except DvcException:
             logger.exception("failed to show metrics")
             return 1
@@ -66,70 +67,41 @@ class CmdMetricsShow(CmdBase):
         return 0
 
 
-class CmdMetricsModify(CmdBase):
-    def run(self):
-        try:
-            self.repo.metrics.modify(
-                self.args.path, typ=self.args.type, xpath=self.args.xpath
-            )
-        except DvcException:
-            logger.exception("failed to modify metric file settings")
-            return 1
+def _show_diff(diff, markdown=False, no_path=False, old=False, precision=None):
+    from collections import OrderedDict
 
-        return 0
+    from dvc.utils.diff import table
 
+    if precision is None:
+        precision = DEFAULT_PRECISION
 
-class CmdMetricsAdd(CmdBase):
-    def run(self):
-        try:
-            self.repo.metrics.add(
-                self.args.path, self.args.type, self.args.xpath
-            )
-        except DvcException:
-            msg = "failed to add metric file '{}'".format(self.args.path)
-            logger.exception(msg)
-            return 1
+    def _round(val):
+        if isinstance(val, float):
+            return round(val, precision)
 
-        return 0
+        return val
 
-
-class CmdMetricsRemove(CmdBase):
-    def run(self):
-        try:
-            self.repo.metrics.remove(self.args.path)
-        except DvcException:
-            msg = "failed to remove metric file '{}'".format(self.args.path)
-            logger.exception(msg)
-            return 1
-
-        return 0
-
-
-def _show_diff(diff):
-    from texttable import Texttable
-
-    if not diff:
-        return "No changes."
-
-    table = Texttable()
-
-    # remove borders to make it easier for users to copy stuff
-    table.set_chars(("", "", "", ""))
-    table.set_deco(0)
-
-    rows = [["Path", "Metric", "Value", "Change"]]
+    rows = []
     for fname, mdiff in diff.items():
-        for metric, change in mdiff.items():
-            rows.append(
-                [
-                    fname,
-                    metric,
-                    change["new"],
-                    change.get("diff", "diff not supported"),
-                ]
-            )
-    table.add_rows(rows)
-    return table.draw()
+        sorted_mdiff = OrderedDict(sorted(mdiff.items()))
+        for metric, change in sorted_mdiff.items():
+            row = [] if no_path else [fname]
+            row.append(metric)
+            if old:
+                row.append(_round(change.get("old")))
+            row.append(_round(change["new"]))
+            row.append(_round(change.get("diff", "diff not supported")))
+            rows.append(row)
+
+    header = [] if no_path else ["Path"]
+    header.append("Metric")
+    if old:
+        header.extend(["Old", "New"])
+    else:
+        header.append("Value")
+    header.append("Change")
+
+    return table(header, rows, markdown)
 
 
 class CmdMetricsDiff(CmdBase):
@@ -139,9 +111,8 @@ class CmdMetricsDiff(CmdBase):
                 a_rev=self.args.a_rev,
                 b_rev=self.args.b_rev,
                 targets=self.args.targets,
-                typ=self.args.type,
-                xpath=self.args.xpath,
                 recursive=self.args.recursive,
+                all=self.args.all,
             )
 
             if self.args.show_json:
@@ -149,7 +120,15 @@ class CmdMetricsDiff(CmdBase):
 
                 logger.info(json.dumps(diff))
             else:
-                logger.info(_show_diff(diff))
+                table = _show_diff(
+                    diff,
+                    self.args.show_md,
+                    self.args.no_path,
+                    self.args.old,
+                    precision=self.args.precision,
+                )
+                if table:
+                    logger.info(table)
 
         except DvcException:
             logger.exception("failed to show metrics diff")
@@ -159,7 +138,7 @@ class CmdMetricsDiff(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
-    METRICS_HELP = "Commands to add, manage, collect and display metrics."
+    METRICS_HELP = "Commands to display and compare metrics."
 
     metrics_parser = subparsers.add_parser(
         "metrics",
@@ -176,7 +155,7 @@ def add_parser(subparsers, parent_parser):
 
     fix_subparsers(metrics_subparsers)
 
-    METRICS_SHOW_HELP = "Output metric values."
+    METRICS_SHOW_HELP = "Print metrics, with optional formatting."
     metrics_show_parser = metrics_subparsers.add_parser(
         "show",
         parents=[parent_parser],
@@ -187,21 +166,11 @@ def add_parser(subparsers, parent_parser):
     metrics_show_parser.add_argument(
         "targets",
         nargs="*",
-        help="Metric files or directories (see -R) to show "
-        "(leave empty to display all)",
-    )
-    metrics_show_parser.add_argument(
-        "-t",
-        "--type",
         help=(
-            "Type of metrics (json/tsv/htsv/csv/hcsv). "
-            "It can be detected by the file extension automatically. "
-            "Unsupported types will be treated as raw."
+            "Limit command scope to these metric files. Using -R, "
+            "directories to search metric files in can also be given."
         ),
-    )
-    metrics_show_parser.add_argument(
-        "-x", "--xpath", help="json/tsv/htsv/csv/hcsv path."
-    )
+    ).complete = completion.FILE
     metrics_show_parser.add_argument(
         "-a",
         "--all-branches",
@@ -216,6 +185,18 @@ def add_parser(subparsers, parent_parser):
         default=False,
         help="Show metrics for all tags.",
     )
+    metrics_show_parser.add_argument(
+        "--all-commits",
+        action="store_true",
+        default=False,
+        help="Show metrics for all commits.",
+    )
+    metrics_show_parser.add_argument(
+        "--show-json",
+        action="store_true",
+        default=False,
+        help="Show output in JSON format.",
+    )
     metrics_show_parser.add_argument(
         "-R",
         "--recursive",
@@ -228,53 +209,10 @@ def add_parser(subparsers, parent_parser):
     )
     metrics_show_parser.set_defaults(func=CmdMetricsShow)
 
-    METRICS_ADD_HELP = "Tag file as a metric file."
-    metrics_add_parser = metrics_subparsers.add_parser(
-        "add",
-        parents=[parent_parser],
-        description=append_doc_link(METRICS_ADD_HELP, "metrics/add"),
-        help=METRICS_ADD_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
+    METRICS_DIFF_HELP = (
+        "Show changes in metrics between commits in the DVC repository, or "
+        "between a commit and the workspace."
     )
-    metrics_add_parser.add_argument(
-        "-t", "--type", help="Type of metrics (raw/json/tsv/htsv/csv/hcsv)."
-    )
-    metrics_add_parser.add_argument(
-        "-x", "--xpath", help="json/tsv/htsv/csv/hcsv path."
-    )
-    metrics_add_parser.add_argument("path", help="Path to a metric file.")
-    metrics_add_parser.set_defaults(func=CmdMetricsAdd)
-
-    METRICS_MODIFY_HELP = "Modify metric file options."
-    metrics_modify_parser = metrics_subparsers.add_parser(
-        "modify",
-        parents=[parent_parser],
-        description=append_doc_link(METRICS_MODIFY_HELP, "metrics/modify"),
-        help=METRICS_MODIFY_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    metrics_modify_parser.add_argument(
-        "-t", "--type", help="Type of metrics (raw/json/tsv/htsv/csv/hcsv)."
-    )
-    metrics_modify_parser.add_argument(
-        "-x", "--xpath", help="json/tsv/htsv/csv/hcsv path."
-    )
-    metrics_modify_parser.add_argument("path", help="Path to a metric file.")
-    metrics_modify_parser.set_defaults(func=CmdMetricsModify)
-
-    METRICS_REMOVE_HELP = "Remove files's metric tag."
-    metrics_remove_parser = metrics_subparsers.add_parser(
-        "remove",
-        parents=[parent_parser],
-        description=append_doc_link(METRICS_REMOVE_HELP, "metrics/remove"),
-        help=METRICS_REMOVE_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    metrics_remove_parser.add_argument("path", help="Path to a metric file.")
-    metrics_remove_parser.set_defaults(func=CmdMetricsRemove)
-
-    METRICS_DIFF_HELP = "Show changes in metrics between commits"
-    " in the DVC repository, or between a commit and the workspace."
     metrics_diff_parser = metrics_subparsers.add_parser(
         "diff",
         parents=[parent_parser],
@@ -288,28 +226,17 @@ def add_parser(subparsers, parent_parser):
     metrics_diff_parser.add_argument(
         "b_rev",
         nargs="?",
-        help=("New Git commit to compare (defaults to the current workspace)"),
+        help="New Git commit to compare (defaults to the current workspace)",
     )
     metrics_diff_parser.add_argument(
         "--targets",
         nargs="*",
         help=(
-            "Metric files or directories (see -R) to show diff for. "
-            "Shows diff for all metric files by default."
+            "Limit command scope to these metric files. Using -R, "
+            "directories to search metric files in can also be given."
         ),
-    )
-    metrics_diff_parser.add_argument(
-        "-t",
-        "--type",
-        help=(
-            "Type of metrics (json/tsv/htsv/csv/hcsv). "
-            "It can be detected by the file extension automatically. "
-            "Unsupported types will be treated as raw."
-        ),
-    )
-    metrics_diff_parser.add_argument(
-        "-x", "--xpath", help="json/tsv/htsv/csv/hcsv path."
-    )
+        metavar="<paths>",
+    ).complete = completion.FILE
     metrics_diff_parser.add_argument(
         "-R",
         "--recursive",
@@ -320,10 +247,43 @@ def add_parser(subparsers, parent_parser):
             "metric files."
         ),
     )
+    metrics_diff_parser.add_argument(
+        "--all",
+        action="store_true",
+        default=False,
+        help="Show unchanged metrics as well.",
+    )
     metrics_diff_parser.add_argument(
         "--show-json",
         action="store_true",
         default=False,
         help="Show output in JSON format.",
     )
+    metrics_diff_parser.add_argument(
+        "--show-md",
+        action="store_true",
+        default=False,
+        help="Show tabulated output in the Markdown format (GFM).",
+    )
+    metrics_diff_parser.add_argument(
+        "--old",
+        action="store_true",
+        default=False,
+        help="Show old metric value.",
+    )
+    metrics_diff_parser.add_argument(
+        "--no-path",
+        action="store_true",
+        default=False,
+        help="Don't show metric path.",
+    )
+    metrics_diff_parser.add_argument(
+        "--precision",
+        type=int,
+        help=(
+            "Round metrics to `n` digits precision after the decimal point. "
+            f"Rounds to {DEFAULT_PRECISION} digits by default."
+        ),
+        metavar="<n>",
+    )
     metrics_diff_parser.set_defaults(func=CmdMetricsDiff)

dvc/command/move.py

@@ -1,11 +1,10 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -38,7 +37,9 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     move_parser.add_argument(
-        "src", help="Source path to a data file or directory."
-    )
-    move_parser.add_argument("dst", help="Destination path.")
+        "src", help="Source path to a data file or directory.",
+    ).complete = completion.FILE
+    move_parser.add_argument(
+        "dst", help="Destination path.",
+    ).complete = completion.FILE
     move_parser.set_defaults(func=CmdMove)

dvc/command/params.py

@@ -0,0 +1,118 @@
+import argparse
+import logging
+from collections import OrderedDict
+
+from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
+from dvc.exceptions import DvcException
+
+logger = logging.getLogger(__name__)
+
+
+def _show_diff(diff, markdown=False, no_path=False):
+    from dvc.utils.diff import table
+
+    rows = []
+    for fname, pdiff in diff.items():
+        sorted_pdiff = OrderedDict(sorted(pdiff.items()))
+        for param, change in sorted_pdiff.items():
+            row = [] if no_path else [fname]
+            row.append(param)
+            row.append(change["old"])
+            row.append(change["new"])
+            rows.append(row)
+
+    header = [] if no_path else ["Path"]
+    header.append("Param")
+    header.append("Old")
+    header.append("New")
+
+    return table(header, rows, markdown)
+
+
+class CmdParamsDiff(CmdBase):
+    def run(self):
+        try:
+            diff = self.repo.params.diff(
+                a_rev=self.args.a_rev,
+                b_rev=self.args.b_rev,
+                all=self.args.all,
+            )
+
+            if self.args.show_json:
+                import json
+
+                logger.info(json.dumps(diff))
+            else:
+                table = _show_diff(diff, self.args.show_md, self.args.no_path)
+                if table:
+                    logger.info(table)
+
+        except DvcException:
+            logger.exception("failed to show params diff")
+            return 1
+
+        return 0
+
+
+def add_parser(subparsers, parent_parser):
+    PARAMS_HELP = "Commands to display params."
+
+    params_parser = subparsers.add_parser(
+        "params",
+        parents=[parent_parser],
+        description=append_doc_link(PARAMS_HELP, "params"),
+        help=PARAMS_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+
+    params_subparsers = params_parser.add_subparsers(
+        dest="cmd",
+        help="Use `dvc params CMD --help` to display command-specific help.",
+    )
+
+    fix_subparsers(params_subparsers)
+
+    PARAMS_DIFF_HELP = (
+        "Show changes in params between commits in the DVC repository, or "
+        "between a commit and the workspace."
+    )
+    params_diff_parser = params_subparsers.add_parser(
+        "diff",
+        parents=[parent_parser],
+        description=append_doc_link(PARAMS_DIFF_HELP, "params/diff"),
+        help=PARAMS_DIFF_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    params_diff_parser.add_argument(
+        "a_rev", nargs="?", help="Old Git commit to compare (defaults to HEAD)"
+    )
+    params_diff_parser.add_argument(
+        "b_rev",
+        nargs="?",
+        help=("New Git commit to compare (defaults to the current workspace)"),
+    )
+    params_diff_parser.add_argument(
+        "--all",
+        action="store_true",
+        default=False,
+        help="Show unchanged params as well.",
+    )
+    params_diff_parser.add_argument(
+        "--show-json",
+        action="store_true",
+        default=False,
+        help="Show output in JSON format.",
+    )
+    params_diff_parser.add_argument(
+        "--show-md",
+        action="store_true",
+        default=False,
+        help="Show tabulated output in the Markdown format (GFM).",
+    )
+    params_diff_parser.add_argument(
+        "--no-path",
+        action="store_true",
+        default=False,
+        help="Don't show params path.",
+    )
+    params_diff_parser.set_defaults(func=CmdParamsDiff)

dvc/command/pipeline.py

@@ -1,247 +0,0 @@
-import argparse
-import logging
-
-from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
-from dvc.exceptions import DvcException
-
-
-logger = logging.getLogger(__name__)
-
-
-class CmdPipelineShow(CmdBase):
-    def _show(self, target, commands, outs, locked):
-        import networkx
-        from dvc.stage import Stage
-
-        stage = Stage.load(self.repo, target)
-        G = self.repo.graph
-        stages = networkx.dfs_postorder_nodes(G, stage)
-
-        if locked:
-            stages = [s for s in stages if s.locked]
-
-        for stage in stages:
-            if commands:
-                if stage.cmd is None:
-                    continue
-                logger.info(stage.cmd)
-            elif outs:
-                for out in stage.outs:
-                    logger.info(str(out))
-            else:
-                logger.info(stage.path_in_repo)
-
-    def _build_graph(self, target, commands, outs):
-        import networkx
-        from dvc.stage import Stage
-        from dvc.repo.graph import get_pipeline
-
-        target_stage = Stage.load(self.repo, target)
-        G = get_pipeline(self.repo.pipelines, target_stage)
-
-        nodes = set()
-        for stage in networkx.dfs_preorder_nodes(G, target_stage):
-            if commands:
-                if stage.cmd is None:
-                    continue
-                nodes.add(stage.cmd)
-            elif outs:
-                for out in stage.outs:
-                    nodes.add(str(out))
-                for dep in stage.deps:
-                    nodes.add(str(dep))
-            else:
-                nodes.add(stage.relpath)
-
-        edges = []
-
-        if outs:
-            for stage in networkx.dfs_preorder_nodes(G, target_stage):
-                for dep in stage.deps:
-                    for out in stage.outs:
-                        edges.append((str(out), str(dep)))
-        else:
-            for from_stage, to_stage in networkx.dfs_edges(G, target_stage):
-                if commands:
-                    if to_stage.cmd is None:
-                        continue
-                    edges.append((from_stage.cmd, to_stage.cmd))
-                else:
-                    edges.append((from_stage.relpath, to_stage.relpath))
-
-        return list(nodes), edges, networkx.is_tree(G)
-
-    def _show_ascii(self, target, commands, outs):
-        from dvc.dagascii import draw
-
-        nodes, edges, _ = self._build_graph(target, commands, outs)
-
-        if not nodes:
-            return
-
-        draw(nodes, edges)
-
-    def _show_dependencies_tree(self, target, commands, outs):
-        from treelib import Tree
-
-        nodes, edges, is_tree = self._build_graph(target, commands, outs)
-        if not nodes:
-            return
-        if not is_tree:
-            raise DvcException(
-                "DAG is not a tree, can not print it in tree-structure way, "
-                "please use --ascii instead"
-            )
-
-        tree = Tree()
-        tree.create_node(target, target)  # Root node
-        observe_list = [target]
-        while len(observe_list) > 0:
-            current_root = observe_list[0]
-            for edge in edges:
-                if edge[0] == current_root:
-                    tree.create_node(edge[1], edge[1], parent=current_root)
-                    observe_list.append(edge[1])
-            observe_list.pop(0)
-        tree.show()
-
-    def _write_dot(self, target, commands, outs):
-        import io
-        import networkx
-        from networkx.drawing.nx_pydot import write_dot
-
-        _, edges, _ = self._build_graph(target, commands, outs)
-        edges = [edge[::-1] for edge in edges]
-
-        simple_g = networkx.DiGraph()
-        simple_g.add_edges_from(edges)
-
-        dot_file = io.StringIO()
-        write_dot(simple_g, dot_file)
-        logger.info(dot_file.getvalue())
-
-    def run(self):
-        if not self.args.targets:
-            self.args.targets = self.default_targets
-
-        for target in self.args.targets:
-            try:
-                if self.args.ascii:
-                    self._show_ascii(
-                        target, self.args.commands, self.args.outs
-                    )
-                elif self.args.dot:
-                    self._write_dot(target, self.args.commands, self.args.outs)
-                elif self.args.tree:
-                    self._show_dependencies_tree(
-                        target, self.args.commands, self.args.outs
-                    )
-                else:
-                    self._show(
-                        target,
-                        self.args.commands,
-                        self.args.outs,
-                        self.args.locked,
-                    )
-            except DvcException:
-                msg = "failed to show pipeline for '{}'".format(target)
-                logger.exception(msg)
-                return 1
-        return 0
-
-
-class CmdPipelineList(CmdBase):
-    def run(self):
-        pipelines = self.repo.pipelines
-        for pipeline in pipelines:
-            for stage in pipeline:
-                logger.info(stage.relpath)
-            if len(pipeline) != 0:
-                logger.info("=" * 80)
-        logger.info("{} pipelines total".format(len(pipelines)))
-
-        return 0
-
-
-def add_parser(subparsers, parent_parser):
-    PIPELINE_HELP = "Manage pipelines."
-    pipeline_parser = subparsers.add_parser(
-        "pipeline",
-        parents=[parent_parser],
-        description=append_doc_link(PIPELINE_HELP, "pipeline"),
-        help=PIPELINE_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-
-    pipeline_subparsers = pipeline_parser.add_subparsers(
-        dest="cmd",
-        help="Use `dvc pipeline CMD --help` for command-specific help.",
-    )
-
-    fix_subparsers(pipeline_subparsers)
-
-    PIPELINE_SHOW_HELP = "Show pipelines."
-    pipeline_show_parser = pipeline_subparsers.add_parser(
-        "show",
-        parents=[parent_parser],
-        description=append_doc_link(PIPELINE_SHOW_HELP, "pipeline/show"),
-        help=PIPELINE_SHOW_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    pipeline_show_group = pipeline_show_parser.add_mutually_exclusive_group()
-    pipeline_show_group.add_argument(
-        "-c",
-        "--commands",
-        action="store_true",
-        default=False,
-        help="Print commands instead of paths to DVC-files.",
-    )
-    pipeline_show_group.add_argument(
-        "-o",
-        "--outs",
-        action="store_true",
-        default=False,
-        help="Print output files instead of paths to DVC-files.",
-    )
-    pipeline_show_parser.add_argument(
-        "-l",
-        "--locked",
-        action="store_true",
-        default=False,
-        help="Print locked DVC stages",
-    )
-    pipeline_show_parser.add_argument(
-        "--ascii",
-        action="store_true",
-        default=False,
-        help="Output DAG as ASCII.",
-    )
-    pipeline_show_parser.add_argument(
-        "--dot",
-        action="store_true",
-        default=False,
-        help="Print DAG with .dot format.",
-    )
-    pipeline_show_parser.add_argument(
-        "--tree",
-        action="store_true",
-        default=False,
-        help="Output DAG as Dependencies Tree.",
-    )
-    pipeline_show_parser.add_argument(
-        "targets",
-        nargs="*",
-        help="DVC-files to show pipeline for. Optional. "
-        "(Finds all DVC-files in the workspace by default.)",
-    )
-    pipeline_show_parser.set_defaults(func=CmdPipelineShow)
-
-    PIPELINE_LIST_HELP = "List pipelines."
-    pipeline_list_parser = pipeline_subparsers.add_parser(
-        "list",
-        parents=[parent_parser],
-        description=append_doc_link(PIPELINE_LIST_HELP, "pipeline/list"),
-        help=PIPELINE_LIST_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    pipeline_list_parser.set_defaults(func=CmdPipelineList)

dvc/command/plots.py

@@ -0,0 +1,233 @@
+import argparse
+import logging
+import os
+
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
+from dvc.exceptions import DvcException
+from dvc.schema import PLOT_PROPS
+from dvc.utils import format_link
+
+logger = logging.getLogger(__name__)
+
+PAGE_HTML = """<!DOCTYPE html>
+<html>
+<head>
+    <title>DVC Plot</title>
+    <script src="https://cdn.jsdelivr.net/npm/[email protected]"></script>
+    <script src="https://cdn.jsdelivr.net/npm/[email protected]"></script>
+    <script src="https://cdn.jsdelivr.net/npm/[email protected]"></script>
+</head>
+<body>
+    {divs}
+</body>
+</html>"""
+
+DIV_HTML = """<div id = "{id}"></div>
+<script type = "text/javascript">
+    var spec = {vega_json};
+    vegaEmbed('#{id}', spec);
+</script>"""
+
+
+class CmdPlots(CmdBase):
+    def _func(self, *args, **kwargs):
+        raise NotImplementedError
+
+    def _props(self):
+        # Pass only props specified by user, to not shadow ones from plot def
+        props = {p: getattr(self.args, p) for p in PLOT_PROPS}
+        return {k: v for k, v in props.items() if v is not None}
+
+    def run(self):
+        if self.args.show_vega:
+            if not self.args.targets:
+                logger.error("please specify a target for `--show-vega`")
+                return 1
+            if len(self.args.targets) > 1:
+                logger.error(
+                    "you can only specify one target for `--show-vega`"
+                )
+                return 1
+
+        try:
+            plots = self._func(targets=self.args.targets, props=self._props())
+
+            if self.args.show_vega:
+                target = self.args.targets[0]
+                logger.info(plots[target])
+                return 0
+
+            divs = [
+                DIV_HTML.format(id=f"plot{i}", vega_json=plot)
+                for i, plot in enumerate(plots.values())
+            ]
+            html = PAGE_HTML.format(divs="\n".join(divs))
+            path = self.args.out or "plots.html"
+
+            with open(path, "w") as fobj:
+                fobj.write(html)
+
+            logger.info(
+                "file://{}".format(os.path.join(self.repo.root_dir, path))
+            )
+
+        except DvcException:
+            logger.exception("")
+            return 1
+
+        return 0
+
+
+class CmdPlotsShow(CmdPlots):
+    def _func(self, *args, **kwargs):
+        return self.repo.plots.show(*args, **kwargs)
+
+
+class CmdPlotsDiff(CmdPlots):
+    def _func(self, *args, **kwargs):
+        return self.repo.plots.diff(*args, revs=self.args.revisions, **kwargs)
+
+
+class CmdPlotsModify(CmdPlots):
+    def run(self):
+        self.repo.plots.modify(
+            self.args.target, props=self._props(), unset=self.args.unset,
+        )
+        return 0
+
+
+def add_parser(subparsers, parent_parser):
+    PLOTS_HELP = (
+        "Commands to visualize and compare plot metrics in structured files "
+        "(JSON, YAML, CSV, TSV)"
+    )
+
+    plots_parser = subparsers.add_parser(
+        "plots",
+        parents=[parent_parser],
+        description=append_doc_link(PLOTS_HELP, "plots"),
+        help=PLOTS_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_subparsers = plots_parser.add_subparsers(
+        dest="cmd",
+        help="Use `dvc plots CMD --help` to display command-specific help.",
+    )
+
+    fix_subparsers(plots_subparsers)
+
+    SHOW_HELP = "Generate plots from metric files."
+    plots_show_parser = plots_subparsers.add_parser(
+        "show",
+        parents=[parent_parser],
+        description=append_doc_link(SHOW_HELP, "plots/show"),
+        help=SHOW_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_show_parser.add_argument(
+        "targets",
+        nargs="*",
+        help="Plots files to visualize. Shows all plots by default.",
+    ).complete = completion.FILE
+    _add_props_arguments(plots_show_parser)
+    _add_output_arguments(plots_show_parser)
+    plots_show_parser.set_defaults(func=CmdPlotsShow)
+
+    PLOTS_DIFF_HELP = (
+        "Show multiple versions of plot metrics "
+        "by plotting them in a single image."
+    )
+    plots_diff_parser = plots_subparsers.add_parser(
+        "diff",
+        parents=[parent_parser],
+        description=append_doc_link(PLOTS_DIFF_HELP, "plots/diff"),
+        help=PLOTS_DIFF_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_diff_parser.add_argument(
+        "--targets",
+        nargs="*",
+        help="Plots file to visualize. Shows all plots by default.",
+        metavar="<path>",
+    ).complete = completion.FILE
+    plots_diff_parser.add_argument(
+        "revisions", nargs="*", default=None, help="Git commits to plot from",
+    )
+    _add_props_arguments(plots_diff_parser)
+    _add_output_arguments(plots_diff_parser)
+    plots_diff_parser.set_defaults(func=CmdPlotsDiff)
+
+    PLOTS_MODIFY_HELP = "Modify display properties of plot metric files."
+    plots_modify_parser = plots_subparsers.add_parser(
+        "modify",
+        parents=[parent_parser],
+        description=append_doc_link(PLOTS_MODIFY_HELP, "plots/modify"),
+        help=PLOTS_MODIFY_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    plots_modify_parser.add_argument(
+        "target", help="Metric file to set properties to",
+    ).complete = completion.FILE
+    _add_props_arguments(plots_modify_parser)
+    plots_modify_parser.add_argument(
+        "--unset",
+        nargs="*",
+        metavar="<property>",
+        help="Unset one or more display properties.",
+    )
+    plots_modify_parser.set_defaults(func=CmdPlotsModify)
+
+
+def _add_props_arguments(parser):
+    parser.add_argument(
+        "-t",
+        "--template",
+        nargs="?",
+        default=None,
+        help=(
+            "Special JSON or HTML schema file to inject with the data. "
+            "See {}".format(
+                format_link("https://man.dvc.org/plots#plot-templates")
+            )
+        ),
+        metavar="<path>",
+    ).complete = completion.FILE
+    parser.add_argument(
+        "-x", default=None, help="Field name for X axis.", metavar="<field>"
+    )
+    parser.add_argument(
+        "-y", default=None, help="Field name for Y axis.", metavar="<field>"
+    )
+    parser.add_argument(
+        "--no-header",
+        action="store_false",
+        dest="header",
+        default=None,  # Use default None to distinguish when it's not used
+        help="Provided CSV or TSV datafile does not have a header.",
+    )
+    parser.add_argument(
+        "--title", default=None, metavar="<text>", help="Plot title."
+    )
+    parser.add_argument(
+        "--x-label", default=None, help="X axis label", metavar="<text>"
+    )
+    parser.add_argument(
+        "--y-label", default=None, help="Y axis label", metavar="<text>"
+    )
+
+
+def _add_output_arguments(parser):
+    parser.add_argument(
+        "-o",
+        "--out",
+        default=None,
+        help="Destination path to save plots to",
+        metavar="<path>",
+    ).complete = completion.DIR
+    parser.add_argument(
+        "--show-vega",
+        action="store_true",
+        default=False,
+        help="Show output in Vega format.",
+    )

dvc/command/remote.py

@@ -1,9 +1,9 @@
 import argparse
 import logging
 
-from dvc.config import ConfigError
 from dvc.command.base import append_doc_link, fix_subparsers
 from dvc.command.config import CmdConfig
+from dvc.config import ConfigError
 from dvc.utils import format_link
 
 logger = logging.getLogger(__name__)
@@ -18,17 +18,13 @@ class CmdRemote(CmdConfig):
 
     def _check_exists(self, conf):
         if self.args.name not in conf["remote"]:
-            raise ConfigError(
-                "remote '{}' doesn't exists.".format(self.args.name)
-            )
+            raise ConfigError(f"remote '{self.args.name}' doesn't exists.")
 
 
 class CmdRemoteAdd(CmdRemote):
     def run(self):
         if self.args.default:
-            logger.info(
-                "Setting '{}' as a default remote.".format(self.args.name)
-            )
+            logger.info(f"Setting '{self.args.name}' as a default remote.")
 
         with self.config.edit(self.args.level) as conf:
             if self.args.name in conf["remote"] and not self.args.force:
@@ -66,7 +62,11 @@ class CmdRemoteModify(CmdRemote):
     def run(self):
         with self.config.edit(self.args.level) as conf:
             self._check_exists(conf)
-            conf["remote"][self.args.name][self.args.option] = self.args.value
+            section = conf["remote"][self.args.name]
+            if self.args.unset:
+                section.pop(self.args.option, None)
+            else:
+                section[self.args.option] = self.args.value
         return 0
 
 
@@ -85,7 +85,18 @@ class CmdRemoteDefault(CmdRemote):
                 if self.args.unset:
                     conf["core"].pop("remote", None)
                 else:
-                    conf["core"]["remote"] = self.args.name
+                    merged_conf = self.config.load_config_to_level(
+                        self.args.level
+                    )
+                    if (
+                        self.args.name in conf["remote"]
+                        or self.args.name in merged_conf["remote"]
+                    ):
+                        conf["core"]["remote"] = self.args.name
+                    else:
+                        raise ConfigError(
+                            "default remote must be present in remote list."
+                        )
         return 0
 
 
@@ -97,10 +108,39 @@ class CmdRemoteList(CmdRemote):
         return 0
 
 
+class CmdRemoteRename(CmdRemote):
+    def _rename_default(self, conf):
+        if conf["core"].get("remote") == self.args.name:
+            conf["core"]["remote"] = self.args.new
+
+    def run(self):
+        all_config = self.config.load_config_to_level(None)
+        if self.args.new in all_config.get("remote", {}):
+            raise ConfigError(
+                "Rename failed. Remote name '{}' already exists.".format(
+                    {self.args.new}
+                )
+            )
+
+        with self.config.edit(self.args.level) as conf:
+            self._check_exists(conf)
+            conf["remote"][self.args.new] = conf["remote"][self.args.name]
+            del conf["remote"][self.args.name]
+            self._rename_default(conf)
+
+        for level in reversed(self.config.LEVELS):
+            if level == self.args.level:
+                break
+            with self.config.edit(level) as level_conf:
+                self._rename_default(level_conf)
+
+        return 0
+
+
 def add_parser(subparsers, parent_parser):
     from dvc.command.config import parent_config_parser
 
-    REMOTE_HELP = "Manage remote storage configuration."
+    REMOTE_HELP = "Set up and manage data remotes."
     remote_parser = subparsers.add_parser(
         "remote",
         parents=[parent_parser],
@@ -116,7 +156,7 @@ def add_parser(subparsers, parent_parser):
 
     fix_subparsers(remote_subparsers)
 
-    REMOTE_ADD_HELP = "Add remote."
+    REMOTE_ADD_HELP = "Add a new data remote."
     remote_add_parser = remote_subparsers.add_parser(
         "add",
         parents=[parent_config_parser, parent_parser],
@@ -147,7 +187,7 @@ def add_parser(subparsers, parent_parser):
     )
     remote_add_parser.set_defaults(func=CmdRemoteAdd)
 
-    REMOTE_DEFAULT_HELP = "Set/unset default remote."
+    REMOTE_DEFAULT_HELP = "Set/unset the default data remote."
     remote_default_parser = remote_subparsers.add_parser(
         "default",
         parents=[parent_config_parser, parent_parser],
@@ -167,20 +207,7 @@ def add_parser(subparsers, parent_parser):
     )
     remote_default_parser.set_defaults(func=CmdRemoteDefault)
 
-    REMOTE_REMOVE_HELP = "Remove remote."
-    remote_remove_parser = remote_subparsers.add_parser(
-        "remove",
-        parents=[parent_config_parser, parent_parser],
-        description=append_doc_link(REMOTE_REMOVE_HELP, "remote/remove"),
-        help=REMOTE_REMOVE_HELP,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    remote_remove_parser.add_argument(
-        "name", help="Name of the remote to remove."
-    )
-    remote_remove_parser.set_defaults(func=CmdRemoteRemove)
-
-    REMOTE_MODIFY_HELP = "Modify remote."
+    REMOTE_MODIFY_HELP = "Modify the configuration of a data remote."
     remote_modify_parser = remote_subparsers.add_parser(
         "modify",
         parents=[parent_config_parser, parent_parser],
@@ -204,7 +231,7 @@ def add_parser(subparsers, parent_parser):
     )
     remote_modify_parser.set_defaults(func=CmdRemoteModify)
 
-    REMOTE_LIST_HELP = "List available remotes."
+    REMOTE_LIST_HELP = "List all available data remotes."
     remote_list_parser = remote_subparsers.add_parser(
         "list",
         parents=[parent_config_parser, parent_parser],
@@ -213,3 +240,27 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     remote_list_parser.set_defaults(func=CmdRemoteList)
+
+    REMOTE_REMOVE_HELP = "Remove a data remote."
+    remote_remove_parser = remote_subparsers.add_parser(
+        "remove",
+        parents=[parent_config_parser, parent_parser],
+        description=append_doc_link(REMOTE_REMOVE_HELP, "remote/remove"),
+        help=REMOTE_REMOVE_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    remote_remove_parser.add_argument(
+        "name", help="Name of the remote to remove."
+    )
+    remote_remove_parser.set_defaults(func=CmdRemoteRemove)
+    REMOTE_RENAME_HELP = "Rename a DVC remote"
+    remote_rename_parser = remote_subparsers.add_parser(
+        "rename",
+        parents=[parent_config_parser, parent_parser],
+        description=append_doc_link(REMOTE_RENAME_HELP, "remote/rename"),
+        help=REMOTE_RENAME_HELP,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    remote_rename_parser.add_argument("name", help="Remote to be renamed")
+    remote_rename_parser.add_argument("new", help="New name of the remote")
+    remote_rename_parser.set_defaults(func=CmdRemoteRename)

dvc/command/remove.py

@@ -1,48 +1,28 @@
 import argparse
 import logging
 
-import dvc.prompt as prompt
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
 class CmdRemove(CmdBase):
-    def _is_outs_only(self, target):
-        if not self.args.purge:
-            return True
-
-        if self.args.force:
-            return False
-
-        msg = "Are you sure you want to remove '{}' with its outputs?".format(
-            target
-        )
-
-        if prompt.confirm(msg):
-            return False
-
-        raise DvcException(
-            "Cannot purge without a confirmation from the user."
-            " Use `-f` to force."
-        )
-
     def run(self):
         for target in self.args.targets:
             try:
-                outs_only = self._is_outs_only(target)
-                self.repo.remove(target, outs_only=outs_only)
+                self.repo.remove(target, outs=self.args.outs)
             except DvcException:
-                logger.exception("failed to remove '{}'".format(target))
+                logger.exception(f"failed to remove '{target}'")
                 return 1
         return 0
 
 
 def add_parser(subparsers, parent_parser):
-    REMOVE_HELP = "Remove DVC-file outputs."
+    REMOVE_HELP = (
+        "Remove stage entry, remove .gitignore entry and unprotect outputs"
+    )
     remove_parser = subparsers.add_parser(
         "remove",
         parents=[parent_parser],
@@ -50,29 +30,13 @@ def add_parser(subparsers, parent_parser):
         help=REMOVE_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
-    remove_parser_group = remove_parser.add_mutually_exclusive_group()
-    remove_parser_group.add_argument(
-        "-o",
+    remove_parser.add_argument(
         "--outs",
         action="store_true",
-        default=True,
-        help="Only remove DVC-file outputs. (Default)",
-    )
-    remove_parser_group.add_argument(
-        "-p",
-        "--purge",
-        action="store_true",
         default=False,
-        help="Remove DVC-file and all its outputs.",
+        help="Remove outputs as well.",
     )
     remove_parser.add_argument(
-        "-f",
-        "--force",
-        action="store_true",
-        default=False,
-        help="Force purge.",
-    )
-    remove_parser.add_argument(
-        "targets", nargs="+", help="DVC-files to remove."
-    )
+        "targets", nargs="+", help="DVC-files to remove.",
+    ).complete = completion.DVC_FILE
     remove_parser.set_defaults(func=CmdRemove)

dvc/command/repro.py

@@ -2,13 +2,13 @@ import argparse
 import logging
 import os
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.command.metrics import show_metrics
 from dvc.command.status import CmdDataStatus
+from dvc.dvcfile import PIPELINE_FILE
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -35,10 +35,11 @@ class CmdRepro(CmdBase):
                     interactive=self.args.interactive,
                     pipeline=self.args.pipeline,
                     all_pipelines=self.args.all_pipelines,
-                    ignore_build_cache=self.args.ignore_build_cache,
+                    run_cache=not self.args.no_run_cache,
                     no_commit=self.args.no_commit,
                     downstream=self.args.downstream,
                     recursive=self.args.recursive,
+                    force_downstream=self.args.force_downstream,
                 )
 
                 if len(stages) == 0:
@@ -57,7 +58,9 @@ class CmdRepro(CmdBase):
 
 
 def add_parser(subparsers, parent_parser):
-    REPRO_HELP = "Check for changes and reproduce stages and dependencies."
+    REPRO_HELP = (
+        "Reproduce complete or partial pipelines by executing their stages."
+    )
     repro_parser = subparsers.add_parser(
         "repro",
         parents=[parent_parser],
@@ -68,8 +71,8 @@ def add_parser(subparsers, parent_parser):
     repro_parser.add_argument(
         "targets",
         nargs="*",
-        help="DVC-file to reproduce. 'Dvcfile' by default.",
-    )
+        help=f"Stages to reproduce. '{PIPELINE_FILE}' by default.",
+    ).complete = completion.DVC_FILE
     repro_parser.add_argument(
         "-f",
         "--force",
@@ -90,6 +93,7 @@ def add_parser(subparsers, parent_parser):
         "--cwd",
         default=os.path.curdir,
         help="Directory within your repo to reproduce from.",
+        metavar="<path>",
     )
     repro_parser.add_argument(
         "-m",
@@ -135,7 +139,16 @@ def add_parser(subparsers, parent_parser):
         help="Reproduce all stages in the specified directory.",
     )
     repro_parser.add_argument(
-        "--ignore-build-cache",
+        "--no-run-cache",
+        action="store_true",
+        default=False,
+        help=(
+            "Execute stage commands even if they have already been run with "
+            "the same command/dependencies/outputs/etc before."
+        ),
+    )
+    repro_parser.add_argument(
+        "--force-downstream",
         action="store_true",
         default=False,
         help="Reproduce all descendants of a changed stage even if their "

dvc/command/root.py

@@ -1,8 +1,7 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBaseNoRepo
+from dvc.command.base import CmdBaseNoRepo, append_doc_link
 from dvc.utils import relpath
 
 logger = logging.getLogger(__name__)
@@ -17,7 +16,7 @@ class CmdRoot(CmdBaseNoRepo):
 
 
 def add_parser(subparsers, parent_parser):
-    ROOT_HELP = "Relative path to the repository's directory."
+    ROOT_HELP = "Return the relative path to the root of the DVC project."
     root_parser = subparsers.add_parser(
         "root",
         parents=[parent_parser],

dvc/command/run.py

@@ -1,18 +1,14 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
 class CmdRun(CmdBase):
     def run(self):
-        overwrite = self.args.yes or self.args.overwrite_dvcfile
-
         if not any(
             [
                 self.args.deps,
@@ -20,15 +16,18 @@ class CmdRun(CmdBase):
                 self.args.outs_no_cache,
                 self.args.metrics,
                 self.args.metrics_no_cache,
+                self.args.plots,
+                self.args.plots_no_cache,
                 self.args.outs_persist,
                 self.args.outs_persist_no_cache,
+                self.args.params,
                 self.args.command,
             ]
         ):  # pragma: no cover
             logger.error(
                 "too few arguments. Specify at least one: `-d`, `-o`, `-O`, "
-                "`-m`, `-M`, `--outs-persist`, `--outs-persist-no-cache`, "
-                "`command`."
+                "`-m`, `-M`, `-p`, `--plots`, `--plots-no-cache`, "
+                "`--outs-persist`, `--outs-persist-no-cache`, `command`."
             )
             return 1
 
@@ -39,21 +38,25 @@ class CmdRun(CmdBase):
                 outs_no_cache=self.args.outs_no_cache,
                 metrics=self.args.metrics,
                 metrics_no_cache=self.args.metrics_no_cache,
+                plots=self.args.plots,
+                plots_no_cache=self.args.plots_no_cache,
                 deps=self.args.deps,
+                params=self.args.params,
                 fname=self.args.file,
-                cwd=self.args.cwd,
                 wdir=self.args.wdir,
                 no_exec=self.args.no_exec,
-                overwrite=overwrite,
-                ignore_build_cache=self.args.ignore_build_cache,
-                remove_outs=self.args.remove_outs,
+                force=self.args.force,
+                run_cache=not self.args.no_run_cache,
                 no_commit=self.args.no_commit,
                 outs_persist=self.args.outs_persist,
                 outs_persist_no_cache=self.args.outs_persist_no_cache,
                 always_changed=self.args.always_changed,
+                name=self.args.name,
+                single_stage=self.args.single_stage,
+                external=self.args.external,
             )
         except DvcException:
-            logger.exception("failed to run command")
+            logger.exception("")
             return 1
 
         return 0
@@ -77,7 +80,7 @@ class CmdRun(CmdBase):
         if " " not in argument or '"' in argument:
             return argument
 
-        return '"{}"'.format(argument)
+        return f'"{argument}"'
 
 
 def add_parser(subparsers, parent_parser):
@@ -95,6 +98,10 @@ def add_parser(subparsers, parent_parser):
         action="append",
         default=[],
         help="Declare dependencies for reproducible cmd.",
+        metavar="<path>",
+    )
+    run_parser.add_argument(
+        "-n", "--name", help="Stage name.",
     )
     run_parser.add_argument(
         "-o",
@@ -102,6 +109,7 @@ def add_parser(subparsers, parent_parser):
         action="append",
         default=[],
         help="Declare output file or directory.",
+        metavar="<filename>",
     )
     run_parser.add_argument(
         "-O",
@@ -110,32 +118,54 @@ def add_parser(subparsers, parent_parser):
         default=[],
         help="Declare output file or directory "
         "(do not put into DVC cache).",
+        metavar="<filename>",
+    )
+    run_parser.add_argument(
+        "-p",
+        "--params",
+        action="append",
+        default=[],
+        help="Declare parameter to use as additional dependency.",
+        metavar="[<filename>:]<params_list>",
     )
     run_parser.add_argument(
         "-m",
         "--metrics",
         action="append",
         default=[],
-        help="Declare output metric file or directory.",
+        help="Declare output metric file.",
+        metavar="<path>",
     )
     run_parser.add_argument(
         "-M",
         "--metrics-no-cache",
         action="append",
         default=[],
-        help="Declare output metric file or directory "
-        "(do not put into DVC cache).",
+        help="Declare output metric file (do not put into DVC cache).",
+        metavar="<path>",
     )
     run_parser.add_argument(
-        "-f", "--file", help="Specify name of the DVC-file it generates."
+        "--plots",
+        action="append",
+        default=[],
+        help="Declare output plot file.",
+        metavar="<path>",
     )
     run_parser.add_argument(
-        "-c", "--cwd", help="Deprecated, use -w and -f instead."
+        "--plots-no-cache",
+        action="append",
+        default=[],
+        help="Declare output plot file (do not put into DVC cache).",
+        metavar="<path>",
+    )
+    run_parser.add_argument(
+        "--file", metavar="<filename>", help=argparse.SUPPRESS,
     )
     run_parser.add_argument(
         "-w",
         "--wdir",
         help="Directory within your repo to run your command in.",
+        metavar="<path>",
     )
     run_parser.add_argument(
         "--no-exec",
@@ -144,30 +174,20 @@ def add_parser(subparsers, parent_parser):
         help="Only create stage file without actually running it.",
     )
     run_parser.add_argument(
-        "-y",
-        "--yes",
+        "-f",
+        "--force",
         action="store_true",
         default=False,
-        help="Deprecated, use --overwrite-dvcfile instead",
+        help="Overwrite existing stage",
     )
     run_parser.add_argument(
-        "--overwrite-dvcfile",
+        "--no-run-cache",
         action="store_true",
         default=False,
-        help="Overwrite existing DVC-file without asking for confirmation.",
-    )
-    run_parser.add_argument(
-        "--ignore-build-cache",
-        action="store_true",
-        default=False,
-        help="Run this stage even if it has been already ran with the same "
-        "command/dependencies/outputs/etc before.",
-    )
-    run_parser.add_argument(
-        "--remove-outs",
-        action="store_true",
-        default=False,
-        help="Deprecated, this is now the default behavior",
+        help=(
+            "Execute the command even if this stage has already been run "
+            "with the same command/dependencies/outputs/etc before."
+        ),
     )
     run_parser.add_argument(
         "--no-commit",
@@ -181,6 +201,7 @@ def add_parser(subparsers, parent_parser):
         default=[],
         help="Declare output file or directory that will not be "
         "removed upon repro.",
+        metavar="<filename>",
     )
     run_parser.add_argument(
         "--outs-persist-no-cache",
@@ -188,6 +209,7 @@ def add_parser(subparsers, parent_parser):
         default=[],
         help="Declare output file or directory that will not be "
         "removed upon repro (do not put into DVC cache).",
+        metavar="<filename>",
     )
     run_parser.add_argument(
         "--always-changed",
@@ -195,6 +217,18 @@ def add_parser(subparsers, parent_parser):
         default=False,
         help="Always consider this DVC-file as changed.",
     )
+    run_parser.add_argument(
+        "--single-stage",
+        action="store_true",
+        default=False,
+        help=argparse.SUPPRESS,
+    )
+    run_parser.add_argument(
+        "--external",
+        action="store_true",
+        default=False,
+        help="Allow outputs that are outside of the DVC repository.",
+    )
     run_parser.add_argument(
         "command", nargs=argparse.REMAINDER, help="Command to execute."
     )

dvc/command/status.py

@@ -2,7 +2,6 @@ import logging
 
 from dvc.command.data_sync import CmdDataBase
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -20,7 +19,7 @@ class CmdDataStatus(CmdDataBase):
         ind = indent * self.STATUS_INDENT
 
         if isinstance(status, str):
-            logger.info("{}{}".format(ind, status))
+            logger.info(f"{ind}{status}")
             return
 
         if isinstance(status, list):
@@ -34,7 +33,7 @@ class CmdDataStatus(CmdDataBase):
             if isinstance(value, str):
                 logger.info("{}{}{}".format(ind, self._normalize(value), key))
             elif value:
-                logger.info("{}{}:".format(ind, key))
+                logger.info(f"{ind}{key}:")
                 self._show(value, indent + 1)
 
     def run(self):
@@ -47,17 +46,24 @@ class CmdDataStatus(CmdDataBase):
                 remote=self.args.remote,
                 all_branches=self.args.all_branches,
                 all_tags=self.args.all_tags,
+                all_commits=self.args.all_commits,
                 with_deps=self.args.with_deps,
+                recursive=self.args.recursive,
             )
-            if st:
-                if self.args.quiet:
-                    return 1
-                else:
-                    self._show(st, indent)
+
+            if self.args.quiet:
+                return bool(st)
+
+            if self.args.show_json:
+                import json
+
+                logger.info(json.dumps(st))
+            elif st:
+                self._show(st, indent)
             else:
                 logger.info(self.UP_TO_DATE_MSG)
 
-        except Exception:
+        except Exception:  # noqa, pylint: disable=broad-except
             logger.exception("failed to obtain data status")
             return 1
         return 0

dvc/command/tag.py

@@ -1,156 +0,0 @@
-import logging
-
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
-from dvc.command.base import fix_subparsers
-from dvc.exceptions import DvcException
-from dvc.utils import to_yaml_string
-
-
-logger = logging.getLogger(__name__)
-
-
-class CmdTagAdd(CmdBase):
-    def run(self):
-        for target in self.args.targets:
-            try:
-                self.repo.tag.add(
-                    self.args.tag,
-                    target=target,
-                    with_deps=self.args.with_deps,
-                    recursive=self.args.recursive,
-                )
-            except DvcException:
-                logger.exception("failed to add tag")
-                return 1
-        return 0
-
-
-class CmdTagRemove(CmdBase):
-    def run(self):
-        for target in self.args.targets:
-            try:
-                self.repo.tag.remove(
-                    self.args.tag,
-                    target=target,
-                    with_deps=self.args.with_deps,
-                    recursive=self.args.recursive,
-                )
-            except DvcException:
-                logger.exception("failed to remove tag")
-                return 1
-        return 0
-
-
-class CmdTagList(CmdBase):
-    def run(self):
-        for target in self.args.targets:
-            try:
-                tags = self.repo.tag.list(
-                    target,
-                    with_deps=self.args.with_deps,
-                    recursive=self.args.recursive,
-                )
-                if tags:
-                    logger.info(to_yaml_string(tags))
-            except DvcException:
-                logger.exception("failed list tags")
-                return 1
-        return 0
-
-
-def add_parser(subparsers, parent_parser):
-    TAG_HELP = "A set of commands to manage DVC tags."
-    tag_parser = subparsers.add_parser(
-        "tag",
-        parents=[parent_parser],
-        description=append_doc_link(TAG_HELP, "tag"),
-        add_help=False,
-    )
-
-    tag_subparsers = tag_parser.add_subparsers(
-        dest="cmd",
-        help="Use DVC tag CMD --help to display command-specific help.",
-    )
-
-    fix_subparsers(tag_subparsers)
-
-    TAG_ADD_HELP = "Add DVC tag."
-    tag_add_parser = tag_subparsers.add_parser(
-        "add",
-        parents=[parent_parser],
-        description=append_doc_link(TAG_ADD_HELP, "tag-add"),
-        help=TAG_ADD_HELP,
-    )
-    tag_add_parser.add_argument("tag", help="Dvc tag.")
-    tag_add_parser.add_argument(
-        "targets", nargs="*", default=[None], help="DVC-files."
-    )
-    tag_add_parser.add_argument(
-        "-d",
-        "--with-deps",
-        action="store_true",
-        default=False,
-        help="Add tag for all dependencies of the specified DVC-file.",
-    )
-    tag_add_parser.add_argument(
-        "-R",
-        "--recursive",
-        action="store_true",
-        default=False,
-        help="Add tag for subdirectories of the specified directory.",
-    )
-    tag_add_parser.set_defaults(func=CmdTagAdd)
-
-    TAG_REMOVE_HELP = "Remove DVC tag."
-    tag_remove_parser = tag_subparsers.add_parser(
-        "remove",
-        parents=[parent_parser],
-        description=append_doc_link(TAG_REMOVE_HELP, "tag-remove"),
-        help=TAG_REMOVE_HELP,
-    )
-    tag_remove_parser.add_argument("tag", help="Dvc tag.")
-    tag_remove_parser.add_argument(
-        "targets", nargs="*", default=[None], help="DVC-files."
-    )
-    tag_remove_parser.add_argument(
-        "-d",
-        "--with-deps",
-        action="store_true",
-        default=False,
-        help="Remove tag for all dependencies of the specified DVC-file.",
-    )
-    tag_remove_parser.add_argument(
-        "-R",
-        "--recursive",
-        action="store_true",
-        default=False,
-        help="Remove tag for subdirectories of the specified directory.",
-    )
-    tag_remove_parser.set_defaults(func=CmdTagRemove)
-
-    TAG_LIST_HELP = "List DVC tags."
-    tag_list_parser = tag_subparsers.add_parser(
-        "list",
-        parents=[parent_parser],
-        description=append_doc_link(TAG_LIST_HELP, "tag-list"),
-        help=TAG_LIST_HELP,
-    )
-    tag_list_parser.add_argument(
-        "targets", nargs="*", default=[None], help="DVC-files."
-    )
-    tag_list_parser.add_argument(
-        "-d",
-        "--with-deps",
-        action="store_true",
-        default=False,
-        help="List tags for all dependencies of the specified DVC-file.",
-    )
-    tag_list_parser.add_argument(
-        "-R",
-        "--recursive",
-        action="store_true",
-        default=False,
-        help="List tags for subdirectories of the specified directory.",
-    )
-    tag_list_parser.set_defaults(func=CmdTagList)

dvc/command/unprotect.py

@@ -1,11 +1,10 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -15,14 +14,17 @@ class CmdUnprotect(CmdBase):
             try:
                 self.repo.unprotect(target)
             except DvcException:
-                msg = "failed to unprotect '{}'".format(target)
+                msg = f"failed to unprotect '{target}'"
                 logger.exception(msg)
                 return 1
         return 0
 
 
 def add_parser(subparsers, parent_parser):
-    UNPROTECT_HELP = "Unprotect data files or directories."
+    UNPROTECT_HELP = (
+        "Unprotect tracked files or directories (when hardlinks or symlinks "
+        "have been enabled with `dvc config cache.type`)"
+    )
     unprotect_parser = subparsers.add_parser(
         "unprotect",
         parents=[parent_parser],
@@ -31,6 +33,6 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     unprotect_parser.add_argument(
-        "targets", nargs="+", help="Data files/directories to unprotect."
-    )
+        "targets", nargs="+", help="Data files/directories to unprotect.",
+    ).complete = completion.FILE
     unprotect_parser.set_defaults(func=CmdUnprotect)

dvc/command/update.py

@@ -1,23 +1,25 @@
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBase
+from dvc.command import completion
+from dvc.command.base import CmdBase, append_doc_link
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
 class CmdUpdate(CmdBase):
     def run(self):
         ret = 0
-        for target in self.args.targets:
-            try:
-                self.repo.update(target, self.args.rev)
-            except DvcException:
-                logger.exception("failed to update '{}'.".format(target))
-                ret = 1
+        try:
+            self.repo.update(
+                targets=self.args.targets,
+                rev=self.args.rev,
+                recursive=self.args.recursive,
+            )
+        except DvcException:
+            logger.exception("failed update data")
+            ret = 1
         return ret
 
 
@@ -31,9 +33,19 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     update_parser.add_argument(
-        "targets", nargs="+", help="DVC-files to update."
+        "targets", nargs="+", help="DVC-files to update.",
+    ).complete = completion.DVC_FILE
+    update_parser.add_argument(
+        "--rev",
+        nargs="?",
+        help="Git revision (e.g. SHA, branch, tag)",
+        metavar="<commit>",
     )
     update_parser.add_argument(
-        "--rev", nargs="?", help="Git revision (e.g. SHA, branch, tag)"
+        "-R",
+        "--recursive",
+        action="store_true",
+        default=False,
+        help="Update all stages in the specified directory.",
     )
     update_parser.set_defaults(func=CmdUpdate)

dvc/command/version.py

@@ -2,21 +2,23 @@ import argparse
 import itertools
 import logging
 import os
+import pathlib
 import platform
 import uuid
-import pathlib
+
+from dvc.command.base import CmdBaseNoRepo, append_doc_link
+from dvc.exceptions import DvcException, NotDvcRepoError
+from dvc.scm.base import SCMError
+from dvc.system import System
+from dvc.utils import is_binary, relpath
+from dvc.utils.pkg import PKG
+from dvc.version import __version__
 
 try:
     import psutil
 except ImportError:
     psutil = None
 
-from dvc.utils import is_binary, relpath
-from dvc.command.base import CmdBaseNoRepo, append_doc_link
-from dvc.version import __version__
-from dvc.exceptions import DvcException, NotDvcRepoError
-from dvc.system import System
-from dvc.utils.pkg import PKG
 
 logger = logging.getLogger(__name__)
 
@@ -26,11 +28,12 @@ class CmdVersion(CmdBaseNoRepo):
         from dvc.repo import Repo
 
         info = [
-            "DVC version: {}".format(__version__),
-            "Python version: {}".format(platform.python_version()),
-            "Platform: {}".format(platform.platform()),
-            "Binary: {}".format(is_binary()),
-            "Package: {}".format(PKG),
+            f"DVC version: {__version__}",
+            f"Python version: {platform.python_version()}",
+            f"Platform: {platform.platform()}",
+            f"Binary: {is_binary()}",
+            f"Package: {PKG}",
+            f"Supported remotes: {self.get_supported_remotes()}",
         ]
 
         try:
@@ -48,7 +51,7 @@ class CmdVersion(CmdBaseNoRepo):
                 if psutil:
                     fs_type = self.get_fs_type(repo.cache.local.cache_dir)
                     info.append(
-                        "Filesystem type (cache directory): {}".format(fs_type)
+                        f"Filesystem type (cache directory): {fs_type}"
                     )
             else:
                 logger.warning(
@@ -61,10 +64,15 @@ class CmdVersion(CmdBaseNoRepo):
 
         except NotDvcRepoError:
             root_directory = os.getcwd()
+        except SCMError:
+            root_directory = os.getcwd()
+            info.append("Repo: dvc, git (broken)")
+        else:
+            info.append("Repo: {}".format(_get_dvc_repo_info(repo)))
 
         if psutil:
             fs_root = self.get_fs_type(os.path.abspath(root_directory))
-            info.append("Filesystem type (workspace): {}".format(fs_root))
+            info.append(f"Filesystem type (workspace): {fs_root}")
 
         logger.info("\n".join(info))
         return 0
@@ -107,15 +115,37 @@ class CmdVersion(CmdBaseNoRepo):
                 os.unlink(dst)
             except DvcException:
                 status = "not supported"
-            cache.append("{name} - {status}".format(name=name, status=status))
+            cache.append(f"{name} - {status}")
         os.remove(src)
 
         return ", ".join(cache)
 
+    @staticmethod
+    def get_supported_remotes():
+        from dvc.remote import TREES
+
+        supported_remotes = []
+        for tree_cls in TREES:
+            if not tree_cls.get_missing_deps():
+                supported_remotes.append(tree_cls.scheme)
+
+        return ", ".join(supported_remotes)
+
+
+def _get_dvc_repo_info(repo):
+    if repo.config.get("core", {}).get("no_scm", False):
+        return "dvc (no_scm)"
+
+    if repo.root_dir != repo.scm.root_dir:
+        return "dvc (subdir), git"
+
+    return "dvc, git"
+
 
 def add_parser(subparsers, parent_parser):
-    VERSION_HELP = "Show DVC version and system/environment information."
-
+    VERSION_HELP = (
+        "Display the DVC version and system/environment information."
+    )
     version_parser = subparsers.add_parser(
         "version",
         parents=[parent_parser],

dvc/compat.py

@@ -1,42 +0,0 @@
-"""Python version compatibility code"""
-
-# Backport os.fspath() from Python 3.6
-try:
-    from os import fspath  # noqa: F821
-
-    fspath_py35 = lambda s: s  # noqa: E731
-except ImportError:
-
-    def fspath(path):
-        """Return the path representation of a path-like object.
-
-        If str or bytes is passed in, it is returned unchanged. Otherwise the
-        os.PathLike interface is used to get the path representation. If the
-        path representation is not str or bytes, TypeError is raised. If the
-        provided path is not str, bytes, or os.PathLike, TypeError is raised.
-        """
-        if isinstance(path, (str, bytes)):
-            return path
-
-        # Work from the object's type to match method resolution of other magic
-        # methods.
-        path_type = type(path)
-        try:
-            path_repr = path_type.__fspath__(path)
-        except AttributeError:
-            if hasattr(path_type, "__fspath__"):
-                raise
-            else:
-                raise TypeError(
-                    "expected str, bytes or os.PathLike object, "
-                    "not " + path_type.__name__
-                )
-        if isinstance(path_repr, (str, bytes)):
-            return path_repr
-        else:
-            raise TypeError(
-                "expected {}.__fspath__() to return str or bytes, "
-                "not {}".format(path_type.__name__, type(path_repr).__name__)
-            )
-
-    fspath_py35 = fspath

dvc/config.py

@@ -1,16 +1,27 @@
 """DVC config objects."""
-from contextlib import contextmanager
 import logging
 import os
 import re
+from contextlib import contextmanager
+from functools import partial
 from urllib.parse import urlparse
 
-from funcy import cached_property, re_find, walk_values, compact
 import configobj
-from voluptuous import Schema, Optional, Invalid, ALLOW_EXTRA
-from voluptuous import All, Any, Lower, Range, Coerce
+from funcy import cached_property, compact, re_find, walk_values
+from voluptuous import (
+    ALLOW_EXTRA,
+    All,
+    Any,
+    Coerce,
+    Invalid,
+    Lower,
+    Optional,
+    Range,
+    Schema,
+)
 
 from dvc.exceptions import DvcException, NotDvcRepoError
+from dvc.path_info import PathInfo
 from dvc.utils import relpath
 
 logger = logging.getLogger(__name__)
@@ -20,7 +31,7 @@ class ConfigError(DvcException):
     """DVC config exception."""
 
     def __init__(self, msg):
-        super().__init__("config file error: {}".format(msg))
+        super().__init__(f"config file error: {msg}")
 
 
 class NoRemoteError(ConfigError):
@@ -78,7 +89,7 @@ def ByUrl(mapping):
         if os.name == "nt" and len(parsed.scheme) == 1 and parsed.netloc == "":
             return schemas[""](data)
         if parsed.scheme not in schemas:
-            raise Invalid("Unsupported URL type {}://".format(parsed.scheme))
+            raise Invalid(f"Unsupported URL type {parsed.scheme}://")
 
         return schemas[parsed.scheme](data)
 
@@ -92,15 +103,22 @@ class RelPath(str):
 REMOTE_COMMON = {
     "url": str,
     "checksum_jobs": All(Coerce(int), Range(1)),
-    "no_traverse": Bool,
+    Optional("no_traverse"): Bool,  # obsoleted
     "verify": Bool,
 }
 LOCAL_COMMON = {
     "type": supported_cache_type,
-    Optional("protected", default=False): Bool,
+    Optional("protected", default=False): Bool,  # obsoleted
     "shared": All(Lower, Choices("group")),
     Optional("slow_link_warning", default=True): Bool,
 }
+HTTP_COMMON = {
+    "auth": All(Lower, Choices("basic", "digest", "custom")),
+    "custom_auth_header": str,
+    "user": str,
+    "password": str,
+    "ask_password": Bool,
+}
 SCHEMA = {
     "core": {
         "remote": Lower,
@@ -108,6 +126,7 @@ SCHEMA = {
         Optional("interactive", default=False): Bool,
         Optional("analytics", default=True): Bool,
         Optional("hardlink_lock", default=False): Bool,
+        Optional("no_scm", default=False): Bool,
     },
     "cache": {
         "local": str,
@@ -132,6 +151,7 @@ SCHEMA = {
                     Optional("listobjects", default=False): Bool,
                     Optional("use_ssl", default=True): Bool,
                     "sse": str,
+                    "sse_kms_key_id": str,
                     "acl": str,
                     "grant_read": str,
                     "grant_read_acp": str,
@@ -164,13 +184,18 @@ SCHEMA = {
                     **REMOTE_COMMON,
                 },
                 "gdrive": {
+                    "gdrive_use_service_account": Bool,
                     "gdrive_client_id": str,
                     "gdrive_client_secret": str,
                     "gdrive_user_credentials_file": str,
+                    "gdrive_service_account_email": str,
+                    "gdrive_service_account_user_email": str,
+                    "gdrive_service_account_p12_file_path": str,
+                    Optional("gdrive_trash_only", default=False): Bool,
                     **REMOTE_COMMON,
                 },
-                "http": REMOTE_COMMON,
-                "https": REMOTE_COMMON,
+                "http": {**HTTP_COMMON, **REMOTE_COMMON},
+                "https": {**HTTP_COMMON, **REMOTE_COMMON},
                 "remote": {str: object},  # Any of the above options are valid
             }
         )
@@ -193,9 +218,8 @@ class Config(dict):
         validate (bool): optional flag to tell dvc if it should validate the
             config or just load it as is. 'True' by default.
 
-
     Raises:
-        ConfigError: thrown when config has an invalid format.
+        ConfigError: thrown if config has an invalid format.
     """
 
     APPNAME = "dvc"
@@ -207,7 +231,9 @@ class Config(dict):
     CONFIG = "config"
     CONFIG_LOCAL = "config.local"
 
-    def __init__(self, dvc_dir=None, validate=True):
+    def __init__(
+        self, dvc_dir=None, validate=True
+    ):  # pylint: disable=super-init-not-called
         self.dvc_dir = dvc_dir
 
         if not dvc_dir:
@@ -264,12 +290,9 @@ class Config(dict):
         """Loads config from all the config files.
 
         Raises:
-            dvc.config.ConfigError: thrown if config has invalid format.
+            ConfigError: thrown if config has an invalid format.
         """
-        conf = {}
-        for level in self.LEVELS:
-            if level in self.files:
-                _merge(conf, self.load_one(level))
+        conf = self.load_config_to_level()
 
         if validate:
             conf = self.validate(conf)
@@ -285,7 +308,7 @@ class Config(dict):
         conf = _load_config(self.files[level])
         conf = self._load_paths(conf, self.files[level])
 
-        # Autovivify sections
+        # Auto-verify sections
         for key in COMPILED_SCHEMA.schema:
             conf.setdefault(key, {})
 
@@ -302,34 +325,56 @@ class Config(dict):
 
         return Config._map_dirs(conf, resolve)
 
+    @staticmethod
+    def _to_relpath(conf_dir, path):
+        if re.match(r"\w+://", path):
+            return path
+
+        if isinstance(path, RelPath) or not os.path.isabs(path):
+            path = relpath(path, conf_dir)
+
+        return PathInfo(path).as_posix()
+
     @staticmethod
     def _save_paths(conf, filename):
         conf_dir = os.path.dirname(filename)
-
-        def rel(path):
-            if re.match(r"\w+://", path):
-                return path
-
-            if isinstance(path, RelPath) or not os.path.isabs(path):
-                return relpath(path, conf_dir)
-            return path
+        rel = partial(Config._to_relpath, conf_dir)
 
         return Config._map_dirs(conf, rel)
 
     @staticmethod
     def _map_dirs(conf, func):
-        dirs_schema = {"cache": {"dir": func}, "remote": {str: {"url": func}}}
+        dirs_schema = {
+            "cache": {"dir": func},
+            "remote": {
+                str: {"url": func, "gdrive_user_credentials_file": func}
+            },
+        }
         return Schema(dirs_schema, extra=ALLOW_EXTRA)(conf)
 
+    def load_config_to_level(self, level=None):
+        merged_conf = {}
+        for merge_level in self.LEVELS:
+            if merge_level == level:
+                break
+            if merge_level in self.files:
+                _merge(merged_conf, self.load_one(merge_level))
+        return merged_conf
+
     @contextmanager
     def edit(self, level="repo"):
         if level in {"repo", "local"} and self.dvc_dir is None:
-            raise ConfigError("Not inside a dvc repo")
+            raise ConfigError("Not inside a DVC repo")
 
         conf = self.load_one(level)
         yield conf
 
         conf = self._save_paths(conf, self.files[level])
+
+        merged_conf = self.load_config_to_level(level)
+        _merge(merged_conf, conf)
+        self.validate(merged_conf)
+
         _save_config(self.files[level], conf)
         self.load()
 
@@ -347,7 +392,7 @@ def _load_config(filename):
 
 
 def _save_config(filename, conf_dict):
-    logger.debug("Writing '{}'.".format(filename))
+    logger.debug(f"Writing '{filename}'.")
     os.makedirs(os.path.dirname(filename), exist_ok=True)
 
     config = configobj.ConfigObj(_pack_remotes(conf_dict))
@@ -374,7 +419,7 @@ def _pack_remotes(conf):
 
     # Transform remote.name -> 'remote "name"'
     for name, val in conf["remote"].items():
-        result['remote "{}"'.format(name)] = val
+        result[f'remote "{name}"'] = val
     result.pop("remote", None)
 
     return result

dvc/daemon.py

@@ -7,9 +7,7 @@ import sys
 from subprocess import Popen
 
 from dvc.env import DVC_DAEMON
-from dvc.utils import fix_env
-from dvc.utils import is_binary
-
+from dvc.utils import fix_env, is_binary
 
 logger = logging.getLogger(__name__)
 
@@ -48,7 +46,6 @@ def _spawn_posix(cmd, env):
         os._exit(1)  # pylint: disable=protected-access
 
     os.setsid()
-    os.umask(0)
 
     try:
         pid = os.fork()
@@ -68,7 +65,7 @@ def _spawn_posix(cmd, env):
 
 
 def _spawn(cmd, env):
-    logger.debug("Trying to spawn '{}'".format(cmd))
+    logger.debug(f"Trying to spawn '{cmd}'")
 
     if os.name == "nt":
         _spawn_windows(cmd, env)
@@ -77,7 +74,7 @@ def _spawn(cmd, env):
     else:
         raise NotImplementedError
 
-    logger.debug("Spawned '{}'".format(cmd))
+    logger.debug(f"Spawned '{cmd}'")
 
 
 def daemon(args):

dvc/dagascii.py

@@ -6,12 +6,9 @@ import os
 import pydoc
 import sys
 
-from grandalf.graphs import Edge
-from grandalf.graphs import Graph
-from grandalf.graphs import Vertex
+from grandalf.graphs import Edge, Graph, Vertex
 from grandalf.layouts import SugiyamaLayout
-from grandalf.routing import EdgeViewer
-from grandalf.routing import route_with_lines
+from grandalf.routing import EdgeViewer, route_with_lines
 
 from dvc.env import DVC_PAGER
 from dvc.utils import format_link
@@ -40,7 +37,7 @@ def find_pager():
     if env_pager:
         return make_pager(env_pager)
 
-    if os.system("({}) 2>{}".format(DEFAULT_PAGER, os.devnull)) == 0:
+    if os.system(f"({DEFAULT_PAGER}) 2>{os.devnull}") == 0:
         return make_pager(DEFAULT_PAGER_FORMATTED)
 
     logger.warning(
@@ -52,7 +49,7 @@ def find_pager():
     return pydoc.plainpager
 
 
-class VertexViewer(object):
+class VertexViewer:
     """Class to define vertex box boundaries that will be accounted for during
     graph building by grandalf.
 
@@ -78,7 +75,7 @@ class VertexViewer(object):
         return self._w
 
 
-class AsciiCanvas(object):
+class AsciiCanvas:
     """Class for drawing in ASCII.
 
     Args:
@@ -95,14 +92,13 @@ class AsciiCanvas(object):
         self.cols = cols
         self.lines = lines
 
-        self.canvas = [[" "] * cols for l in range(lines)]
+        self.canvas = [[" "] * cols for line in range(lines)]
 
     def draw(self):
         """Draws ASCII canvas on the screen."""
-        pager = find_pager()
         lines = map("".join, self.canvas)
         joined_lines = os.linesep.join(lines)
-        pager(joined_lines)
+        return joined_lines
 
     def point(self, x, y, char):
         """Create a point on ASCII canvas.
@@ -148,21 +144,21 @@ class AsciiCanvas(object):
                 if dx == 0:
                     y = y0
                 else:
-                    y = y0 + int(round((x - x0) * dy / float((dx))))
+                    y = y0 + int(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 + int(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 + int(round((y - y1) * dx / float(dy)))
                 self.point(x, y, char)
 
     def text(self, x, y, text):
@@ -216,7 +212,7 @@ def _build_sugiyama_layout(vertexes, edges):
     # Y
     #
 
-    vertexes = {v: Vertex(" {} ".format(v)) for v in vertexes}
+    vertexes = {v: Vertex(f" {v} ") for v in vertexes}
     # NOTE: reverting edges to correctly orientate the graph
     edges = [Edge(vertexes[e], vertexes[s]) for s, e in edges]
     vertexes = vertexes.values()
@@ -226,7 +222,7 @@ def _build_sugiyama_layout(vertexes, edges):
         vertex.view = VertexViewer(vertex.data)
 
     # NOTE: determine min box length to create the best layout
-    minw = min([v.view.w for v in vertexes])
+    minw = min(v.view.w for v in vertexes)
 
     for edge in edges:
         edge.view = EdgeViewer()
@@ -319,4 +315,4 @@ def draw(vertexes, edges):
             int(round(x - minx)) + 1, int(round(y - miny)) + 1, vertex.data
         )
 
-    canvas.draw()
+    return canvas.draw()

dvc/data_cloud.py

@@ -3,13 +3,12 @@
 import logging
 
 from dvc.config import NoRemoteError
-from dvc.remote import Remote
-
+from dvc.remote import get_remote
 
 logger = logging.getLogger(__name__)
 
 
-class DataCloud(object):
+class DataCloud:
     """Class that manages dvc remotes.
 
     Args:
@@ -23,12 +22,12 @@ class DataCloud(object):
     def __init__(self, repo):
         self.repo = repo
 
-    def get_remote(self, remote=None, command="<command>"):
-        if not remote:
-            remote = self.repo.config["core"].get("remote")
+    def get_remote(self, name=None, command="<command>"):
+        if not name:
+            name = self.repo.config["core"].get("remote")
 
-        if remote:
-            return self._init_remote(remote)
+        if name:
+            return self._init_remote(name)
 
         if bool(self.repo.config["remote"]):
             error_msg = (
@@ -45,55 +44,60 @@ class DataCloud(object):
 
         raise NoRemoteError(error_msg)
 
-    def _init_remote(self, remote):
-        return Remote(self.repo, name=remote)
+    def _init_remote(self, name):
+        return get_remote(self.repo, name=name)
 
-    def push(self, cache, jobs=None, remote=None, show_checksums=False):
+    def push(
+        self, cache, jobs=None, remote=None, show_checksums=False,
+    ):
         """Push data items in a cloud-agnostic way.
 
         Args:
             cache (NamedCache): named checksums to push to the cloud.
             jobs (int): number of jobs that can be running simultaneously.
-            remote (dvc.remote.base.RemoteBASE): optional remote to push to.
+            remote (dvc.remote.base.BaseRemote): optional remote to push to.
                 By default remote from core.remote config option is used.
             show_checksums (bool): show checksums instead of file names in
                 information messages.
         """
+        remote = self.get_remote(remote, "push")
+
         return self.repo.cache.local.push(
-            cache,
-            jobs=jobs,
-            remote=self.get_remote(remote, "push"),
-            show_checksums=show_checksums,
+            cache, jobs=jobs, remote=remote, show_checksums=show_checksums,
         )
 
-    def pull(self, cache, jobs=None, remote=None, show_checksums=False):
+    def pull(
+        self, cache, jobs=None, remote=None, show_checksums=False,
+    ):
         """Pull data items in a cloud-agnostic way.
 
         Args:
             cache (NamedCache): named checksums to pull from the cloud.
             jobs (int): number of jobs that can be running simultaneously.
-            remote (dvc.remote.base.RemoteBASE): optional remote to pull from.
+            remote (dvc.remote.base.BaseRemote): optional remote to pull from.
                 By default remote from core.remote config option is used.
             show_checksums (bool): show checksums instead of file names in
                 information messages.
         """
         remote = self.get_remote(remote, "pull")
+
         downloaded_items_num = self.repo.cache.local.pull(
             cache, jobs=jobs, remote=remote, show_checksums=show_checksums
         )
 
-        if not remote.verify:
+        if not remote.tree.verify:
             self._save_pulled_checksums(cache)
 
         return downloaded_items_num
 
     def _save_pulled_checksums(self, cache):
-        for checksum in cache["local"].keys():
-            cache_file = self.repo.cache.local.checksum_to_path_info(checksum)
-            if self.repo.cache.local.exists(cache_file):
-                # We can safely save here, as existing corrupted files will be
-                # removed upon status, while files corrupted during download
-                # will not be moved from tmp_file (see `RemoteBASE.download()`)
+        for checksum in cache.scheme_keys("local"):
+            cache_file = self.repo.cache.local.hash_to_path_info(checksum)
+            if self.repo.cache.local.tree.exists(cache_file):
+                # We can safely save here, as existing corrupted files will
+                # be removed upon status, while files corrupted during
+                # download will not be moved from tmp_file
+                # (see `RemoteBASE.download()`)
                 self.repo.state.save(cache_file, checksum)
 
     def status(self, cache, jobs=None, remote=None, show_checksums=False):
@@ -102,7 +106,7 @@ class DataCloud(object):
         Args:
             cache (NamedCache): named checksums to check status for.
             jobs (int): number of jobs that can be running simultaneously.
-            remote (dvc.remote.base.RemoteBASE): optional remote to compare
+            remote (dvc.remote.base.BaseRemote): optional remote to compare
                 cache to. By default remote from core.remote config option
                 is used.
             show_checksums (bool): show checksums instead of file names in

dvc/dependency/__init__.py

@@ -1,37 +1,42 @@
+from collections import defaultdict
 from urllib.parse import urlparse
 
 import dvc.output as output
-from dvc.dependency.gs import DependencyGS
-from dvc.dependency.hdfs import DependencyHDFS
-from dvc.dependency.http import DependencyHTTP
-from dvc.dependency.https import DependencyHTTPS
-from dvc.dependency.local import DependencyLOCAL
-from dvc.dependency.s3 import DependencyS3
-from dvc.dependency.ssh import DependencySSH
-from dvc.output.base import OutputBase
-from dvc.remote import Remote
+from dvc.dependency.azure import AzureDependency
+from dvc.dependency.gs import GSDependency
+from dvc.dependency.hdfs import HDFSDependency
+from dvc.dependency.http import HTTPDependency
+from dvc.dependency.https import HTTPSDependency
+from dvc.dependency.local import LocalDependency
+from dvc.dependency.param import ParamsDependency
+from dvc.dependency.s3 import S3Dependency
+from dvc.dependency.ssh import SSHDependency
+from dvc.output.base import BaseOutput
+from dvc.remote import get_remote
 from dvc.scheme import Schemes
-from .repo import DependencyREPO
 
+from .repo import RepoDependency
 
 DEPS = [
-    DependencyGS,
-    DependencyHDFS,
-    DependencyHTTP,
-    DependencyHTTPS,
-    DependencyS3,
-    DependencySSH,
-    # NOTE: DependencyLOCAL is the default choice
+    AzureDependency,
+    GSDependency,
+    HDFSDependency,
+    HTTPDependency,
+    HTTPSDependency,
+    S3Dependency,
+    SSHDependency,
+    # NOTE: LocalDependency is the default choice
 ]
 
 DEP_MAP = {
-    Schemes.LOCAL: DependencyLOCAL,
-    Schemes.SSH: DependencySSH,
-    Schemes.S3: DependencyS3,
-    Schemes.GS: DependencyGS,
-    Schemes.HDFS: DependencyHDFS,
-    Schemes.HTTP: DependencyHTTP,
-    Schemes.HTTPS: DependencyHTTPS,
+    Schemes.LOCAL: LocalDependency,
+    Schemes.SSH: SSHDependency,
+    Schemes.S3: S3Dependency,
+    Schemes.AZURE: AzureDependency,
+    Schemes.GS: GSDependency,
+    Schemes.HDFS: HDFSDependency,
+    Schemes.HTTP: HTTPDependency,
+    Schemes.HTTPS: HTTPSDependency,
 }
 
 
@@ -40,39 +45,69 @@ DEP_MAP = {
 # cached, see -o and -O flags for `dvc run`) and 'metric' (whether or not
 # output is a metric file and how to parse it, see `-M` flag for `dvc run`).
 SCHEMA = output.SCHEMA.copy()
-del SCHEMA[OutputBase.PARAM_CACHE]
-del SCHEMA[OutputBase.PARAM_METRIC]
-SCHEMA[DependencyREPO.PARAM_REPO] = DependencyREPO.REPO_SCHEMA
+del SCHEMA[BaseOutput.PARAM_CACHE]
+del SCHEMA[BaseOutput.PARAM_METRIC]
+SCHEMA.update(RepoDependency.REPO_SCHEMA)
+SCHEMA.update(ParamsDependency.PARAM_SCHEMA)
 
 
 def _get(stage, p, info):
-    parsed = urlparse(p)
-
-    if parsed.scheme == "remote":
-        remote = Remote(stage.repo, name=parsed.netloc)
+    parsed = urlparse(p) if p else None
+    if parsed and parsed.scheme == "remote":
+        remote = get_remote(stage.repo, name=parsed.netloc)
         return DEP_MAP[remote.scheme](stage, p, info, remote=remote)
 
-    if info and info.get(DependencyREPO.PARAM_REPO):
-        repo = info.pop(DependencyREPO.PARAM_REPO)
-        return DependencyREPO(repo, stage, p, info)
+    if info and info.get(RepoDependency.PARAM_REPO):
+        repo = info.pop(RepoDependency.PARAM_REPO)
+        return RepoDependency(repo, stage, p, info)
+
+    if info and info.get(ParamsDependency.PARAM_PARAMS):
+        params = info.pop(ParamsDependency.PARAM_PARAMS)
+        return ParamsDependency(stage, p, params)
 
     for d in DEPS:
         if d.supported(p):
             return d(stage, p, info)
-    return DependencyLOCAL(stage, p, info)
+    return LocalDependency(stage, p, info)
 
 
 def loadd_from(stage, d_list):
     ret = []
     for d in d_list:
-        p = d.pop(OutputBase.PARAM_PATH)
+        p = d.pop(BaseOutput.PARAM_PATH, None)
         ret.append(_get(stage, p, d))
     return ret
 
 
 def loads_from(stage, s_list, erepo=None):
-    ret = []
-    for s in s_list:
-        info = {DependencyREPO.PARAM_REPO: erepo} if erepo else {}
-        ret.append(_get(stage, s, info))
-    return ret
+    assert isinstance(s_list, list)
+    info = {RepoDependency.PARAM_REPO: erepo} if erepo else {}
+    return [_get(stage, s, info.copy()) for s in s_list]
+
+
+def _merge_params(s_list):
+    d = defaultdict(list)
+    default_file = ParamsDependency.DEFAULT_PARAMS_FILE
+    for key in s_list:
+        if isinstance(key, str):
+            d[default_file].append(key)
+            continue
+        if not isinstance(key, dict):
+            msg = "Only list of str/dict is supported. Got: "
+            msg += f"'{type(key).__name__}'."
+            raise ValueError(msg)
+
+        for k, params in key.items():
+            if not isinstance(params, list):
+                msg = "Expected list of params for custom params file "
+                msg += f"'{k}', got '{type(params).__name__}'."
+                raise ValueError(msg)
+            d[k].extend(params)
+    return d
+
+
+def loads_params(stage, s_list):
+    d = _merge_params(s_list)
+    return [
+        ParamsDependency(stage, path, params) for path, params in d.items()
+    ]

dvc/dependency/azure.py

@@ -0,0 +1,7 @@
+from dvc.dependency.base import BaseDependency
+from dvc.output.base import BaseOutput
+from dvc.remote.azure import AzureRemoteTree
+
+
+class AzureDependency(BaseDependency, BaseOutput):
+    TREE_CLS = AzureRemoteTree

dvc/dependency/base.py

@@ -3,24 +3,22 @@ from dvc.exceptions import DvcException
 
 class DependencyDoesNotExistError(DvcException):
     def __init__(self, path):
-        msg = "dependency '{}' does not exist".format(path)
+        msg = f"dependency '{path}' does not exist"
         super().__init__(msg)
 
 
 class DependencyIsNotFileOrDirError(DvcException):
     def __init__(self, path):
-        msg = "dependency '{}' is not a file or directory".format(path)
+        msg = f"dependency '{path}' is not a file or directory"
         super().__init__(msg)
 
 
 class DependencyIsStageFileError(DvcException):
     def __init__(self, path):
-        super().__init__(
-            "Stage file '{}' cannot be a dependency.".format(path)
-        )
+        super().__init__(f"Stage file '{path}' cannot be a dependency.")
 
 
-class DependencyBase(object):
+class BaseDependency:
     IS_DEPENDENCY = True
 
     DoesNotExistError = DependencyDoesNotExistError

dvc/dependency/gs.py

@@ -1,6 +1,6 @@
-from dvc.dependency.base import DependencyBase
-from dvc.output.gs import OutputGS
+from dvc.dependency.base import BaseDependency
+from dvc.output.gs import GSOutput
 
 
-class DependencyGS(DependencyBase, OutputGS):
+class GSDependency(BaseDependency, GSOutput):
     pass

dvc/dependency/hdfs.py

@@ -1,6 +1,6 @@
-from dvc.dependency.base import DependencyBase
-from dvc.output.hdfs import OutputHDFS
+from dvc.dependency.base import BaseDependency
+from dvc.output.hdfs import HDFSOutput
 
 
-class DependencyHDFS(DependencyBase, OutputHDFS):
+class HDFSDependency(BaseDependency, HDFSOutput):
     pass

dvc/dependency/http.py

@@ -1,7 +1,7 @@
-from dvc.dependency.base import DependencyBase
-from dvc.output.base import OutputBase
-from dvc.remote.http import RemoteHTTP
+from dvc.dependency.base import BaseDependency
+from dvc.output.base import BaseOutput
+from dvc.remote.http import HTTPRemoteTree
 
 
-class DependencyHTTP(DependencyBase, OutputBase):
-    REMOTE = RemoteHTTP
+class HTTPDependency(BaseDependency, BaseOutput):
+    TREE_CLS = HTTPRemoteTree

dvc/dependency/https.py

@@ -1,6 +1,7 @@
-from .http import DependencyHTTP
-from dvc.remote.https import RemoteHTTPS
+from dvc.remote.https import HTTPSRemoteTree
+
+from .http import HTTPDependency
 
 
-class DependencyHTTPS(DependencyHTTP):
-    REMOTE = RemoteHTTPS
+class HTTPSDependency(HTTPDependency):
+    TREE_CLS = HTTPSRemoteTree

dvc/dependency/local.py

@@ -1,6 +1,6 @@
-from dvc.dependency.base import DependencyBase
-from dvc.output.local import OutputLOCAL
+from dvc.dependency.base import BaseDependency
+from dvc.output.local import LocalOutput
 
 
-class DependencyLOCAL(DependencyBase, OutputLOCAL):
+class LocalDependency(BaseDependency, LocalOutput):
     pass

dvc/dependency/param.py

@@ -0,0 +1,116 @@
+import os
+from collections import defaultdict
+
+import dpath.util
+import yaml
+from voluptuous import Any
+
+from dvc.dependency.local import LocalDependency
+from dvc.exceptions import DvcException
+
+
+class MissingParamsError(DvcException):
+    pass
+
+
+class BadParamFileError(DvcException):
+    pass
+
+
+class ParamsDependency(LocalDependency):
+    PARAM_PARAMS = "params"
+    PARAM_SCHEMA = {PARAM_PARAMS: Any(dict, list, None)}
+    DEFAULT_PARAMS_FILE = "params.yaml"
+
+    def __init__(self, stage, path, params):
+        info = {}
+        self.params = []
+        if params:
+            if isinstance(params, list):
+                self.params = params
+            else:
+                assert isinstance(params, dict)
+                self.params = list(params.keys())
+                info = params
+
+        super().__init__(
+            stage,
+            path
+            or os.path.join(stage.repo.root_dir, self.DEFAULT_PARAMS_FILE),
+            info=info,
+        )
+
+    def fill_values(self, values=None):
+        """Load params values dynamically."""
+        if not values:
+            return
+        for param in self.params:
+            value = values.get(param)
+            if value:
+                self.info[param] = value
+
+    def save(self):
+        super().save()
+        self.info = self.save_info()
+
+    def status(self):
+        status = super().status()
+
+        if status[str(self)] == "deleted":
+            return status
+
+        status = defaultdict(dict)
+        info = self.read_params()
+        for param in self.params:
+            if param not in info.keys():
+                st = "deleted"
+            elif param not in self.info:
+                st = "new"
+            elif info[param] != self.info[param]:
+                st = "modified"
+            else:
+                assert info[param] == self.info[param]
+                continue
+
+            status[str(self)][param] = st
+
+        return status
+
+    def dumpd(self):
+        return {
+            self.PARAM_PATH: self.def_path,
+            self.PARAM_PARAMS: self.info or self.params,
+        }
+
+    def read_params(self):
+        if not self.exists:
+            return {}
+
+        with self.repo.tree.open(self.path_info, "r") as fobj:
+            try:
+                config = yaml.safe_load(fobj)
+            except yaml.YAMLError as exc:
+                raise BadParamFileError(
+                    f"Unable to read parameters from '{self}'"
+                ) from exc
+
+        ret = {}
+        for param in self.params:
+            try:
+                ret[param] = dpath.util.get(config, param, separator=".")
+            except KeyError:
+                pass
+        return ret
+
+    def save_info(self):
+        info = self.read_params()
+
+        missing_params = set(self.params) - set(info.keys())
+        if missing_params:
+            raise MissingParamsError(
+                "Parameters '{}' are missing from '{}'.".format(
+                    ", ".join(missing_params), self,
+                )
+            )
+
+        return info

dvc/dependency/repo.py

@@ -2,21 +2,24 @@ import os
 
 from voluptuous import Required
 
-from .local import DependencyLOCAL
 from dvc.exceptions import OutputNotFoundError
 from dvc.path_info import PathInfo
 
+from .local import LocalDependency
 
-class DependencyREPO(DependencyLOCAL):
+
+class RepoDependency(LocalDependency):
     PARAM_REPO = "repo"
     PARAM_URL = "url"
     PARAM_REV = "rev"
     PARAM_REV_LOCK = "rev_lock"
 
     REPO_SCHEMA = {
-        Required(PARAM_URL): str,
-        PARAM_REV: str,
-        PARAM_REV_LOCK: str,
+        PARAM_REPO: {
+            Required(PARAM_URL): str,
+            PARAM_REV: str,
+            PARAM_REV_LOCK: str,
+        }
     }
 
     def __init__(self, def_repo, stage, *args, **kwargs):
@@ -47,13 +50,22 @@ class DependencyREPO(DependencyLOCAL):
         return external_repo(d["url"], rev=rev)
 
     def _get_checksum(self, locked=True):
+        from dvc.repo.tree import RepoTree
+
         with self._make_repo(locked=locked) as repo:
             try:
                 return repo.find_out_by_relpath(self.def_path).info["md5"]
             except OutputNotFoundError:
                 path = PathInfo(os.path.join(repo.root_dir, self.def_path))
+
+                # we want stream but not fetch, so DVC out directories are
+                # walked, but dir contents is not fetched
+                tree = RepoTree(repo, stream=True)
+
                 # We are polluting our repo cache with some dir listing here
-                return self.repo.cache.local.get_checksum(path)
+                if tree.isdir(path):
+                    return self.repo.cache.local.get_hash(path, tree=tree)
+                return tree.get_file_hash(path)
 
     def status(self):
         current_checksum = self._get_checksum(locked=True)
@@ -73,16 +85,16 @@ class DependencyREPO(DependencyLOCAL):
     def download(self, to):
         with self._make_repo() as repo:
             if self.def_repo.get(self.PARAM_REV_LOCK) is None:
-                self.def_repo[self.PARAM_REV_LOCK] = repo.scm.get_rev()
+                self.def_repo[self.PARAM_REV_LOCK] = repo.get_rev()
 
-            if hasattr(repo, "cache"):
-                repo.cache.local.cache_dir = self.repo.cache.local.cache_dir
-
-            repo.pull_to(self.def_path, to.path_info)
+            cache = self.repo.cache.local
+            with repo.use_cache(cache):
+                _, _, cache_infos = repo.fetch_external([self.def_path])
+            cache.checkout(to.path_info, cache_infos[0])
 
     def update(self, rev=None):
         if rev:
             self.def_repo[self.PARAM_REV] = rev
 
         with self._make_repo(locked=False) as repo:
-            self.def_repo[self.PARAM_REV_LOCK] = repo.scm.get_rev()
+            self.def_repo[self.PARAM_REV_LOCK] = repo.get_rev()

dvc/dependency/s3.py

@@ -1,6 +1,6 @@
-from dvc.dependency.base import DependencyBase
-from dvc.output.s3 import OutputS3
+from dvc.dependency.base import BaseDependency
+from dvc.output.s3 import S3Output
 
 
-class DependencyS3(DependencyBase, OutputS3):
+class S3Dependency(BaseDependency, S3Output):
     pass

dvc/dependency/ssh.py

@@ -1,6 +1,6 @@
-from dvc.dependency.base import DependencyBase
-from dvc.output.ssh import OutputSSH
+from dvc.dependency.base import BaseDependency
+from dvc.output.ssh import SSHOutput
 
 
-class DependencySSH(DependencyBase, OutputSSH):
+class SSHDependency(BaseDependency, SSHOutput):
     pass

dvc/dvcfile.py

@@ -0,0 +1,301 @@
+import collections
+import contextlib
+import logging
+import os
+
+from voluptuous import MultipleInvalid
+
+from dvc.exceptions import DvcException
+from dvc.stage import serialize
+from dvc.stage.exceptions import (
+    StageFileBadNameError,
+    StageFileDoesNotExistError,
+    StageFileFormatError,
+    StageFileIsNotDvcFileError,
+)
+from dvc.stage.loader import SingleStageLoader, StageLoader
+from dvc.utils import relpath
+from dvc.utils.collections import apply_diff
+from dvc.utils.yaml import dump_yaml, parse_yaml, parse_yaml_for_update
+
+logger = logging.getLogger(__name__)
+
+DVC_FILE = "Dvcfile"
+DVC_FILE_SUFFIX = ".dvc"
+PIPELINE_FILE = "dvc.yaml"
+PIPELINE_LOCK = "dvc.lock"
+
+
+class LockfileCorruptedError(DvcException):
+    pass
+
+
+def is_valid_filename(path):
+    return path.endswith(DVC_FILE_SUFFIX) or os.path.basename(path) in [
+        DVC_FILE,
+        PIPELINE_FILE,
+    ]
+
+
+def is_dvc_file(path):
+    return os.path.isfile(path) and (
+        is_valid_filename(path) or os.path.basename(path) == PIPELINE_LOCK
+    )
+
+
+def check_dvc_filename(path):
+    if not is_valid_filename(path):
+        raise StageFileBadNameError(
+            "bad DVC-file name '{}'. DVC-files should be named "
+            "'Dvcfile' or have a '.dvc' suffix (e.g. '{}.dvc').".format(
+                relpath(path), os.path.basename(path)
+            )
+        )
+
+
+class FileMixin:
+    SCHEMA = None
+
+    def __init__(self, repo, path, **kwargs):
+        self.repo = repo
+        self.path = path
+
+    def __repr__(self):
+        return "{}: {}".format(
+            self.__class__.__name__, relpath(self.path, self.repo.root_dir)
+        )
+
+    def __hash__(self):
+        return hash(self.path)
+
+    def __eq__(self, other):
+        return self.repo == other.repo and os.path.abspath(
+            self.path
+        ) == os.path.abspath(other.path)
+
+    def __str__(self):
+        return f"{self.__class__.__name__}: {self.relpath}"
+
+    @property
+    def relpath(self):
+        return relpath(self.path)
+
+    def exists(self):
+        return self.repo.tree.exists(self.path)
+
+    def _load(self):
+        # it raises the proper exceptions by priority:
+        # 1. when the file doesn't exists
+        # 2. filename is not a DVC-file
+        # 3. path doesn't represent a regular file
+        if not self.exists():
+            raise StageFileDoesNotExistError(self.path)
+        check_dvc_filename(self.path)
+        if not self.repo.tree.isfile(self.path):
+            raise StageFileIsNotDvcFileError(self.path)
+
+        with self.repo.tree.open(self.path) as fd:
+            stage_text = fd.read()
+        d = parse_yaml(stage_text, self.path)
+        self.validate(d, self.relpath)
+        return d, stage_text
+
+    @classmethod
+    def validate(cls, d, fname=None):
+        assert isinstance(cls.SCHEMA, collections.abc.Callable)
+        try:
+            cls.SCHEMA(d)  # pylint: disable=not-callable
+        except MultipleInvalid as exc:
+            raise StageFileFormatError(f"'{fname}' format error: {exc}")
+
+    def remove(self, force=False):  # pylint: disable=unused-argument
+        with contextlib.suppress(FileNotFoundError):
+            os.unlink(self.path)
+
+    def dump(self, stage, **kwargs):
+        raise NotImplementedError
+
+
+class SingleStageFile(FileMixin):
+    from dvc.schema import COMPILED_SINGLE_STAGE_SCHEMA as SCHEMA
+
+    @property
+    def stage(self):
+        data, raw = self._load()
+        return SingleStageLoader.load_stage(self, data, raw)
+
+    @property
+    def stages(self):
+        data, raw = self._load()
+        return SingleStageLoader(self, data, raw)
+
+    def dump(self, stage, **kwargs):
+        """Dumps given stage appropriately in the dvcfile."""
+        from dvc.stage import PipelineStage
+
+        assert not isinstance(stage, PipelineStage)
+        check_dvc_filename(self.path)
+        logger.debug(
+            "Saving information to '{file}'.".format(file=relpath(self.path))
+        )
+        dump_yaml(self.path, serialize.to_single_stage_file(stage))
+        self.repo.scm.track_file(self.relpath)
+
+    def remove_stage(self, stage):  # pylint: disable=unused-argument
+        self.remove()
+
+
+class PipelineFile(FileMixin):
+    """Abstraction for pipelines file, .yaml + .lock combined."""
+
+    from dvc.schema import COMPILED_MULTI_STAGE_SCHEMA as SCHEMA
+
+    @property
+    def _lockfile(self):
+        return Lockfile(self.repo, os.path.splitext(self.path)[0] + ".lock")
+
+    def dump(
+        self, stage, update_pipeline=False, no_lock=False, **kwargs
+    ):  # pylint: disable=arguments-differ
+        """Dumps given stage appropriately in the dvcfile."""
+        from dvc.stage import PipelineStage
+
+        assert isinstance(stage, PipelineStage)
+        check_dvc_filename(self.path)
+
+        if update_pipeline and not stage.is_data_source:
+            self._dump_pipeline_file(stage)
+
+        if not no_lock:
+            self._dump_lockfile(stage)
+
+    def _dump_lockfile(self, stage):
+        self._lockfile.dump(stage)
+
+    def _dump_pipeline_file(self, stage):
+        data = {}
+        if self.exists():
+            with open(self.path) as fd:
+                data = parse_yaml_for_update(fd.read(), self.path)
+        else:
+            logger.info("Creating '%s'", self.relpath)
+            open(self.path, "w+").close()
+
+        data["stages"] = data.get("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]
+            if "meta" in orig_stage_data:
+                stage_data[stage.name]["meta"] = orig_stage_data["meta"]
+            apply_diff(stage_data[stage.name], orig_stage_data)
+        else:
+            data["stages"].update(stage_data)
+
+        dump_yaml(self.path, data)
+        self.repo.scm.track_file(self.relpath)
+
+    @property
+    def stage(self):
+        raise DvcException(
+            "PipelineFile has multiple stages. Please specify it's name."
+        )
+
+    @property
+    def stages(self):
+        data, _ = self._load()
+        lockfile_data = self._lockfile.load()
+        return StageLoader(self, data.get("stages", {}), lockfile_data)
+
+    def remove(self, force=False):
+        if not force:
+            logger.warning("Cannot remove pipeline file.")
+            return
+
+        super().remove()
+        self._lockfile.remove()
+
+    def remove_stage(self, stage):
+        self._lockfile.remove_stage(stage)
+        if not self.exists():
+            return
+
+        with open(self.path, "r") as f:
+            d = parse_yaml_for_update(f.read(), self.path)
+
+        self.validate(d, self.path)
+        if stage.name not in d.get("stages", {}):
+            return
+
+        logger.debug("Removing '%s' from '%s'", stage.name, self.path)
+        del d["stages"][stage.name]
+        dump_yaml(self.path, d)
+
+
+class Lockfile(FileMixin):
+    from dvc.schema import COMPILED_LOCKFILE_SCHEMA as SCHEMA
+
+    def load(self):
+        if not self.exists():
+            return {}
+        with self.repo.tree.open(self.path) as fd:
+            data = parse_yaml(fd.read(), self.path)
+        try:
+            self.validate(data, fname=self.relpath)
+        except StageFileFormatError:
+            raise LockfileCorruptedError(
+                f"Lockfile '{self.relpath}' is corrupted."
+            )
+        return data
+
+    def dump(self, stage, **kwargs):
+        stage_data = serialize.to_lockfile(stage)
+        if not self.exists():
+            modified = True
+            logger.info("Generating lock file '%s'", self.relpath)
+            data = stage_data
+            open(self.path, "w+").close()
+        else:
+            with self.repo.tree.open(self.path, "r") as fd:
+                data = parse_yaml_for_update(fd.read(), self.path)
+            modified = data.get(stage.name, {}) != stage_data.get(
+                stage.name, {}
+            )
+            if modified:
+                logger.info("Updating lock file '%s'", self.relpath)
+            data.update(stage_data)
+        dump_yaml(self.path, data)
+        if modified:
+            self.repo.scm.track_file(self.relpath)
+
+    def remove_stage(self, stage):
+        if not self.exists():
+            return
+
+        with open(self.path) as f:
+            d = parse_yaml_for_update(f.read(), self.path)
+        self.validate(d, self.path)
+
+        if stage.name not in d:
+            return
+
+        logger.debug("Removing '%s' from '%s'", stage.name, self.path)
+        del d[stage.name]
+
+        dump_yaml(self.path, d)
+
+
+class Dvcfile:
+    def __new__(cls, repo, path, **kwargs):
+        assert path
+        assert repo
+
+        _, ext = os.path.splitext(path)
+        if ext in [".yaml", ".yml"]:
+            return PipelineFile(repo, path, **kwargs)
+        # fallback to single stage file for better error messages
+        return SingleStageFile(repo, path, **kwargs)

dvc/exceptions.py

@@ -1,11 +1,20 @@
 """Exceptions raised by the dvc."""
+from funcy import first
 
-from dvc.utils import relpath, format_link
+from dvc.utils import format_link, relpath
 
 
 class DvcException(Exception):
     """Base class for all dvc exceptions."""
 
+    def __init__(self, msg, *args):
+        assert msg
+        super().__init__(msg, *args)
+
+
+class InvalidArgumentError(ValueError, DvcException):
+    """Thrown if arguments are invalid."""
+
 
 class OutputDuplicationError(DvcException):
     """Thrown if a file/directory is specified as an output in more than one
@@ -19,12 +28,17 @@ class OutputDuplicationError(DvcException):
     def __init__(self, output, stages):
         assert isinstance(output, str)
         assert all(hasattr(stage, "relpath") for stage in stages)
-        msg = (
-            "file/directory '{}' is specified as an output in more than one "
-            "stage: {}\n"
-            "This is not allowed. Consider using a different output name."
-        ).format(output, "\n    ".join(s.relpath for s in stages))
+        if len(stages) == 1:
+            msg = "output '{}' is already specified in {}.".format(
+                output, first(stages)
+            )
+        else:
+            msg = "output '{}' is already specified in stages:\n{}".format(
+                output, "\n".join(f"\t- {s.addressing}" for s in stages),
+            )
         super().__init__(msg)
+        self.stages = stages
+        self.output = output
 
 
 class OutputNotFoundError(DvcException):
@@ -56,8 +70,8 @@ class StagePathAsOutputError(DvcException):
     def __init__(self, stage, output):
         assert isinstance(output, str)
         super().__init__(
-            "'{stage}' is within an output '{output}' of another stage".format(
-                stage=stage.relpath, output=output
+            "{stage} is within an output '{output}' of another stage".format(
+                stage=stage, output=output
             )
         )
 
@@ -73,10 +87,7 @@ class CircularDependencyError(DvcException):
     def __init__(self, dependency):
         assert isinstance(dependency, str)
 
-        msg = (
-            "file/directory '{}' is specified as an output and as a "
-            "dependency."
-        )
+        msg = "'{}' is specified as an output and as a dependency."
         super().__init__(msg.format(dependency))
 
 
@@ -90,7 +101,7 @@ class ArgumentDuplicationError(DvcException):
 
     def __init__(self, path):
         assert isinstance(path, str)
-        super().__init__("file '{}' is specified more than once.".format(path))
+        super().__init__(f"file '{path}' is specified more than once.")
 
 
 class MoveNotDataSourceError(DvcException):
@@ -125,12 +136,8 @@ class DvcParserError(DvcException):
 class CyclicGraphError(DvcException):
     def __init__(self, stages):
         assert isinstance(stages, list)
-        stages = "\n".join("\t- {}".format(stage.relpath) for stage in stages)
-        msg = (
-            "you've introduced a cycle in your pipeline that involves "
-            "the following stages:"
-            "\n"
-            "{stages}".format(stages=stages)
+        msg = "Pipeline has a cycle involving: {}.".format(
+            ", ".join(s.addressing for s in stages)
         )
         super().__init__(msg)
 
@@ -138,7 +145,7 @@ class CyclicGraphError(DvcException):
 class ConfirmRemoveError(DvcException):
     def __init__(self, path):
         super().__init__(
-            "unable to remove '{}' without a confirmation from the user. Use "
+            "unable to remove '{}' without a confirmation. Use "
             "`-f` to force.".format(path)
         )
 
@@ -150,7 +157,7 @@ class InitError(DvcException):
 class ReproductionError(DvcException):
     def __init__(self, dvc_file_name):
         self.path = dvc_file_name
-        super().__init__("failed to reproduce '{}'".format(dvc_file_name))
+        super().__init__(f"failed to reproduce '{dvc_file_name}'")
 
 
 class BadMetricError(DvcException):
@@ -158,7 +165,7 @@ class BadMetricError(DvcException):
         super().__init__(
             "the following metrics do not exist, "
             "are not metric files or are malformed: {paths}".format(
-                paths=", ".join("'{}'".format(path) for path in paths)
+                paths=", ".join(f"'{path}'" for path in paths)
             )
         )
 
@@ -166,17 +173,24 @@ class BadMetricError(DvcException):
 class NoMetricsError(DvcException):
     def __init__(self):
         super().__init__(
-            "no metric files in this repository. "
-            "Use `dvc metrics add` to add a metric file to track."
+            "no metric files in this repository. Use `-m/-M` options for "
+            "`dvc run` to mark stage outputs as  metrics."
         )
 
 
-class StageFileCorruptedError(DvcException):
+class NoPlotsError(DvcException):
+    def __init__(self):
+        super().__init__(
+            "no plots in this repository. Use `--plots/--plots-no-cache` "
+            "options for `dvc run` to mark stage outputs as plots."
+        )
+
+
+class YAMLFileCorruptedError(DvcException):
     def __init__(self, path):
         path = relpath(path)
         super().__init__(
-            "unable to read DVC-file: {} "
-            "YAML file structure is corrupted".format(path)
+            f"unable to read: '{path}', YAML file structure is corrupted"
         )
 
 
@@ -196,7 +210,7 @@ class OverlappingOutputPathsError(DvcException):
 
 class CheckoutErrorSuggestGit(DvcException):
     def __init__(self, target):
-        super().__init__("Did you mean `git checkout {}`?".format(target))
+        super().__init__(f"Did you mean `git checkout {target}`?")
 
 
 class ETagMismatchError(DvcException):
@@ -208,10 +222,11 @@ class ETagMismatchError(DvcException):
 
 
 class FileMissingError(DvcException):
-    def __init__(self, path):
+    def __init__(self, path, hint=None):
         self.path = path
+        hint = "" if hint is None else f". {hint}"
         super().__init__(
-            "Can't find '{}' neither locally nor on remote".format(path)
+            f"Can't find '{path}' neither locally nor on remote{hint}"
         )
 
 
@@ -237,25 +252,23 @@ class DownloadError(DvcException):
     def __init__(self, amount):
         self.amount = amount
 
-        super().__init__(
-            "{amount} files failed to download".format(amount=amount)
-        )
+        super().__init__(f"{amount} files failed to download")
 
 
 class UploadError(DvcException):
     def __init__(self, amount):
         self.amount = amount
 
-        super().__init__(
-            "{amount} files failed to upload".format(amount=amount)
-        )
+        super().__init__(f"{amount} files failed to upload")
 
 
 class CheckoutError(DvcException):
-    def __init__(self, target_infos):
+    def __init__(self, target_infos, stats=None):
+        self.target_infos = target_infos
+        self.stats = stats
         targets = [str(t) for t in target_infos]
         m = (
-            "Checkout failed for following targets:\n {}\nDid you "
+            "Checkout failed for following targets:\n{}\nDid you "
             "forget to fetch?".format("\n".join(targets))
         )
         super().__init__(m)
@@ -268,7 +281,7 @@ class CollectCacheError(DvcException):
 class NoRemoteInExternalRepoError(DvcException):
     def __init__(self, url):
         super().__init__(
-            "No DVC remote is specified in target repository '{}'.".format(url)
+            f"No DVC remote is specified in target repository '{url}'."
         )
 
 
@@ -283,27 +296,23 @@ class NoOutputInExternalRepoError(DvcException):
 
 class HTTPError(DvcException):
     def __init__(self, code, reason):
-        super().__init__("'{} {}'".format(code, reason))
+        super().__init__(f"'{code} {reason}'")
 
 
 class PathMissingError(DvcException):
     default_msg = (
         "The path '{}' does not exist in the target repository '{}'"
-        " neither as an output nor a git-handled file."
+        " neither as a DVC output nor as a Git-tracked file."
     )
-    default_msg_output_only = (
+    default_msg_dvc_only = (
         "The path '{}' does not exist in the target repository '{}'"
-        " as an output."
+        " as an DVC output."
     )
 
-    def __init__(self, path, repo, output_only=False):
-        msg = (
-            self.default_msg
-            if not output_only
-            else self.default_msg_output_only
-        )
+    def __init__(self, path, repo, dvc_only=False):
+        msg = self.default_msg if not dvc_only else self.default_msg_dvc_only
         super().__init__(msg.format(path, repo))
-        self.output_only = output_only
+        self.dvc_only = dvc_only
 
 
 class RemoteCacheRequiredError(DvcException):
@@ -319,3 +328,19 @@ class RemoteCacheRequiredError(DvcException):
                 format_link("https://man.dvc.org/config#cache"),
             )
         )
+
+
+class IsADirectoryError(DvcException):  # noqa,pylint:disable=redefined-builtin
+    """Raised when a file operation is requested on a directory."""
+
+
+class NoOutputOrStageError(DvcException):
+    """
+    Raised when the target is neither an output nor a stage name in dvc.yaml
+    """
+
+    def __init__(self, target, file):
+        super().__init__(
+            f"'{target}' "
+            f"does not exist as an output or a stage name in '{file}'"
+        )

dvc/external_repo.py

@@ -1,35 +1,41 @@
 import logging
 import os
 import tempfile
+import threading
 from contextlib import contextmanager
 from distutils.dir_util import copy_tree
-import threading
+from typing import Iterable
 
-from funcy import retry, suppress, wrap_with, cached_property
+from funcy import cached_property, retry, wrap_with
 
-from dvc.path_info import PathInfo
-from dvc.compat import fspath
-from dvc.repo import Repo
 from dvc.config import NoRemoteError, NotDvcRepoError
-from dvc.exceptions import NoRemoteInExternalRepoError
-from dvc.exceptions import OutputNotFoundError, NoOutputInExternalRepoError
-from dvc.exceptions import FileMissingError, PathMissingError
-from dvc.utils.fs import remove, fs_copy, move
-from dvc.utils import tmp_fname
+from dvc.exceptions import (
+    FileMissingError,
+    NoOutputInExternalRepoError,
+    NoRemoteInExternalRepoError,
+    OutputNotFoundError,
+    PathMissingError,
+)
+from dvc.path_info import PathInfo
+from dvc.repo import Repo
+from dvc.repo.tree import RepoTree
 from dvc.scm.git import Git
-
+from dvc.scm.tree import is_working_tree
+from dvc.utils.fs import remove
 
 logger = logging.getLogger(__name__)
 
 
 @contextmanager
 def external_repo(url, rev=None, for_write=False):
-    logger.debug("Creating external repo {}@{}", url, rev)
+    logger.debug("Creating external repo %s@%s", url, rev)
     path = _cached_clone(url, rev, for_write=for_write)
+    if not rev:
+        rev = "HEAD"
     try:
-        repo = ExternalRepo(path, url)
+        repo = ExternalRepo(path, url, rev, for_write=for_write)
     except NotDvcRepoError:
-        repo = ExternalGitRepo(path, url)
+        repo = ExternalGitRepo(path, url, rev)
 
     try:
         yield repo
@@ -61,58 +67,100 @@ def clean_repos():
         _remove(path)
 
 
-class ExternalRepo(Repo):
-    def __init__(self, root_dir, url):
-        super().__init__(root_dir)
+class BaseExternalRepo:
+    # pylint: disable=no-member
+
+    _local_cache = None
+
+    @property
+    def local_cache(self):
+        if hasattr(self, "cache"):
+            return self.cache.local
+        return self._local_cache
+
+    @contextmanager
+    def use_cache(self, cache):
+        """Use the specified cache in place of default tmpdir cache for
+        download operations.
+        """
+        if hasattr(self, "cache"):
+            save_cache = self.cache.local
+            self.cache.local = cache
+        self._local_cache = cache
+
+        yield
+
+        if hasattr(self, "cache"):
+            self.cache.local = save_cache
+        self._local_cache = None
+
+    @cached_property
+    def repo_tree(self):
+        return RepoTree(self, fetch=True)
+
+    def get_rev(self):
+        if is_working_tree(self.tree):
+            return self.scm.get_rev()
+        if hasattr(self.tree, "tree"):
+            return self.tree.tree.rev
+        return self.tree.rev
+
+    def fetch_external(self, paths: Iterable, **kwargs):
+        """Fetch specified external repo paths into cache.
+
+        Returns 3-tuple in the form
+            (downloaded, failed, list(cache_infos))
+        where cache_infos can be used as checkout targets for the
+        fetched paths.
+        """
+        download_results = []
+        failed = 0
+
+        paths = [PathInfo(self.root_dir) / path for path in paths]
+
+        def download_update(result):
+            download_results.append(result)
+
+        save_infos = []
+        for path in paths:
+            if not self.repo_tree.exists(path):
+                raise PathMissingError(path, self.url)
+            save_info = self.local_cache.save(
+                path,
+                self.repo_tree,
+                None,
+                save_link=False,
+                download_callback=download_update,
+            )
+            save_infos.append(save_info)
+
+        return sum(download_results), failed, save_infos
+
+    def get_external(self, path, dest):
+        """Convenience wrapper for fetch_external and checkout."""
+        if self.local_cache:
+            # fetch DVC and git files to tmpdir cache, then checkout
+            _, _, save_infos = self.fetch_external([path])
+            self.local_cache.checkout(PathInfo(dest), save_infos[0])
+        else:
+            # git-only erepo with no cache, just copy files directly
+            # to dest
+            path = PathInfo(self.root_dir) / path
+            if not self.repo_tree.exists(path):
+                raise PathMissingError(path, self.url)
+            self.repo_tree.copytree(path, dest)
+
+
+class ExternalRepo(Repo, BaseExternalRepo):
+    def __init__(self, root_dir, url, rev, for_write=False):
+        if for_write:
+            super().__init__(root_dir)
+        else:
+            root_dir = os.path.realpath(root_dir)
+            super().__init__(root_dir, scm=Git(root_dir), rev=rev)
         self.url = url
         self._set_cache_dir()
-        self._set_upstream()
-
-    def pull_to(self, path, to_info):
-        """
-        Pull the corresponding file or directory specified by `path` and
-        checkout it into `to_info`.
-
-        It works with files tracked by Git and DVC, and also local files
-        outside the repository.
-        """
-        out = None
-        path_info = PathInfo(self.root_dir) / path
-
-        with suppress(OutputNotFoundError):
-            (out,) = self.find_outs_by_path(fspath(path_info), strict=False)
-
-        try:
-            if out and out.use_cache:
-                self._pull_cached(out, path_info, to_info)
-                return
-
-            # Check if it is handled by Git (it can't have an absolute path)
-            if os.path.isabs(path):
-                raise FileNotFoundError
-
-            fs_copy(fspath(path_info), fspath(to_info))
-        except FileNotFoundError:
-            raise PathMissingError(path, self.url)
-
-    def _pull_cached(self, out, path_info, dest):
-        with self.state:
-            tmp = PathInfo(tmp_fname(dest))
-            src = tmp / path_info.relative_to(out.path_info)
-
-            out.path_info = tmp
-
-            # Only pull unless all needed cache is present
-            if out.changed_cache(filter_info=src):
-                self.cloud.pull(out.get_used_cache(filter_info=src))
-
-            failed = out.checkout(filter_info=src)
-
-            move(src, dest)
-            remove(tmp)
-
-            if failed:
-                raise FileNotFoundError
+        self._fix_upstream()
 
     @wrap_with(threading.Lock())
     def _set_cache_dir(self):
@@ -122,28 +170,52 @@ class ExternalRepo(Repo):
             cache_dir = CACHE_DIRS[self.url] = tempfile.mkdtemp("dvc-cache")
 
         self.cache.local.cache_dir = cache_dir
+        self._local_cache = self.cache.local
 
-    def _set_upstream(self):
-        # check if the URL is local and no default remote is present
-        # add default remote pointing to the original repo's cache location
-        if os.path.isdir(self.url):
-            if not self.config["core"].get("remote"):
-                src_repo = Repo(self.url)
-                try:
-                    cache_dir = src_repo.cache.local.cache_dir
-                finally:
-                    src_repo.close()
+    def _fix_upstream(self):
+        if not os.path.isdir(self.url):
+            return
 
-                self.config["remote"]["auto-generated-upstream"] = {
-                    "url": cache_dir
-                }
-                self.config["core"]["remote"] = "auto-generated-upstream"
+        try:
+            src_repo = Repo(self.url)
+        except NotDvcRepoError:
+            # If ExternalRepo does not throw NotDvcRepoError and Repo does,
+            # the self.url might be a bare git repo.
+            # NOTE: This will fail to resolve remote with relative path,
+            # same as if it was a remote DVC repo.
+            return
+
+        try:
+            remote_name = self.config["core"].get("remote")
+            if remote_name:
+                self._fix_local_remote(src_repo, remote_name)
+            else:
+                self._add_upstream(src_repo)
+        finally:
+            src_repo.close()
+
+    def _fix_local_remote(self, src_repo, remote_name):
+        # If a remote URL is relative to the source repo,
+        # it will have changed upon config load and made
+        # relative to this new repo. Restore the old one here.
+        new_remote = self.config["remote"][remote_name]
+        old_remote = src_repo.config["remote"][remote_name]
+        if new_remote["url"] != old_remote["url"]:
+            new_remote["url"] = old_remote["url"]
+
+    def _add_upstream(self, src_repo):
+        # Fill the empty upstream entry with a new remote pointing to the
+        # original repo's cache location.
+        cache_dir = src_repo.cache.local.cache_dir
+        self.config["remote"]["auto-generated-upstream"] = {"url": cache_dir}
+        self.config["core"]["remote"] = "auto-generated-upstream"
 
 
-class ExternalGitRepo:
-    def __init__(self, root_dir, url):
-        self.root_dir = root_dir
+class ExternalGitRepo(BaseExternalRepo):
+    def __init__(self, root_dir, url, rev):
+        self.root_dir = os.path.realpath(root_dir)
         self.url = url
+        self.tree = self.scm.get_tree(rev)
 
     @cached_property
     def scm(self):
@@ -156,22 +228,15 @@ class ExternalGitRepo:
     def find_out_by_relpath(self, path):
         raise OutputNotFoundError(path, self)
 
-    def pull_to(self, path, to_info):
-        try:
-            # Git handled files can't have absolute path
-            if os.path.isabs(path):
-                raise FileNotFoundError
-
-            fs_copy(os.path.join(self.root_dir, path), fspath(to_info))
-        except FileNotFoundError:
-            raise PathMissingError(path, self.url)
-
     @contextmanager
     def open_by_relpath(self, path, mode="r", encoding=None, **kwargs):
+        """Opens a specified resource as a file object."""
+        tree = RepoTree(self)
         try:
-            abs_path = os.path.join(self.root_dir, path)
-            with open(abs_path, mode, encoding=encoding) as fd:
-                yield fd
+            with tree.open(
+                path, mode=mode, encoding=encoding, **kwargs
+            ) as fobj:
+                yield fobj
         except FileNotFoundError:
             raise PathMissingError(path, self.url)
 
@@ -183,25 +248,23 @@ def _cached_clone(url, rev, for_write=False):
     revision checked out. If for_write is set prevents reusing this dir via
     cache.
     """
-    if not for_write and Git.is_sha(rev) and (url, rev) in CLONES:
-        return CLONES[url, rev]
-
+    # even if we have already cloned this repo, we may need to
+    # fetch/fast-forward to get specified rev
     clone_path = _clone_default_branch(url, rev)
-    rev_sha = Git(clone_path).resolve_rev(rev or "HEAD")
 
-    if not for_write and (url, rev_sha) in CLONES:
-        return CLONES[url, rev_sha]
+    if not for_write and (url) in CLONES:
+        return CLONES[url]
 
     # Copy to a new dir to keep the clone clean
     repo_path = tempfile.mkdtemp("dvc-erepo")
+    logger.debug("erepo: making a copy of %s clone", url)
     copy_tree(clone_path, repo_path)
 
     # Check out the specified revision
-    if rev is not None:
+    if for_write:
         _git_checkout(repo_path, rev)
-
-    if not for_write:
-        CLONES[url, rev_sha] = repo_path
+    else:
+        CLONES[url] = repo_path
     return repo_path
 
 
@@ -219,8 +282,10 @@ def _clone_default_branch(url, rev):
             git = Git(clone_path)
             # Do not pull for known shas, branches and tags might move
             if not Git.is_sha(rev) or not git.has_rev(rev):
+                logger.debug("erepo: git pull %s", url)
                 git.pull()
         else:
+            logger.debug("erepo: git clone %s to a temporary dir", url)
             clone_path = tempfile.mkdtemp("dvc-clone")
             git = Git.clone(url, clone_path)
             CLONES[url] = clone_path
@@ -232,6 +297,7 @@ def _clone_default_branch(url, rev):
 
 
 def _git_checkout(repo_path, rev):
+    logger.debug("erepo: git checkout %s@%s", repo_path, rev)
     git = Git(repo_path)
     try:
         git.checkout(rev)

dvc/ignore.py

@@ -1,17 +1,21 @@
 import logging
 import os
+import re
+from itertools import groupby
 
 from funcy import cached_property
-from pathspec import PathSpec
 from pathspec.patterns import GitWildMatchPattern
+from pathspec.util import normalize_file
 
+from dvc.path_info import PathInfo
 from dvc.scm.tree import BaseTree
+from dvc.system import System
 from dvc.utils import relpath
 
 logger = logging.getLogger(__name__)
 
 
-class DvcIgnore(object):
+class DvcIgnore:
     DVCIGNORE_FILE = ".dvcignore"
 
     def __call__(self, root, dirs, files):
@@ -26,7 +30,17 @@ class DvcIgnorePatterns(DvcIgnore):
         self.dirname = os.path.normpath(os.path.dirname(ignore_file_path))
 
         with tree.open(ignore_file_path, encoding="utf-8") as fobj:
-            self.ignore_spec = PathSpec.from_lines(GitWildMatchPattern, fobj)
+            path_spec_lines = fobj.readlines()
+            regex_pattern_list = map(
+                GitWildMatchPattern.pattern_to_regex, path_spec_lines
+            )
+            self.ignore_spec = [
+                (ignore, re.compile("|".join(item[0] for item in group)))
+                for ignore, group in groupby(
+                    regex_pattern_list, lambda x: x[1]
+                )
+                if ignore is not None
+            ]
 
     def __call__(self, root, dirs, files):
         files = [f for f in files if not self.matches(root, f)]
@@ -35,12 +49,28 @@ class DvcIgnorePatterns(DvcIgnore):
         return dirs, files
 
     def matches(self, dirname, basename):
-        abs_path = os.path.join(dirname, basename)
-        rel_path = relpath(abs_path, self.dirname)
-
-        if os.pardir + os.sep in rel_path:
+        # NOTE: `relpath` is too slow, so we have to assume that both
+        # `dirname` and `self.dirname` are relative or absolute together.
+        prefix = self.dirname + os.sep
+        if dirname == self.dirname:
+            path = basename
+        elif dirname.startswith(prefix):
+            rel = dirname[len(prefix) :]
+            # NOTE: `os.path.join` is ~x5.5 slower
+            path = f"{rel}{os.sep}{basename}"
+        else:
             return False
-        return self.ignore_spec.match_file(rel_path)
+
+        if not System.is_unix():
+            path = normalize_file(path)
+        return self.ignore(path)
+
+    def ignore(self, path):
+        result = False
+        for ignore, pattern in self.ignore_spec:
+            if pattern.match(path):
+                result = ignore
+        return result
 
     def __hash__(self):
         return hash(self.ignore_file_path)
@@ -71,11 +101,27 @@ class DvcIgnoreDirs(DvcIgnore):
         return self.basenames == other.basenames
 
 
-class DvcIgnoreFilter(object):
-    def __init__(self, tree):
+class DvcIgnoreRepo(DvcIgnore):
+    def __call__(self, root, dirs, files):
+        def is_dvc_repo(directory):
+            from dvc.repo import Repo
+
+            return os.path.isdir(os.path.join(root, directory, Repo.DVC_DIR))
+
+        dirs = [d for d in dirs if not is_dvc_repo(d)]
+
+        return dirs, files
+
+
+class DvcIgnoreFilter:
+    def __init__(self, tree, root_dir):
         self.tree = tree
-        self.ignores = {DvcIgnoreDirs([".git", ".hg", ".dvc"])}
-        for root, dirs, files in self.tree.walk(self.tree.tree_root):
+        self.root_dir = root_dir
+        self.ignores = {
+            DvcIgnoreDirs([".git", ".hg", ".dvc"]),
+            DvcIgnoreRepo(),
+        }
+        for root, dirs, files in self.tree.walk(self.root_dir):
             self._update(root)
             dirs[:], files[:] = self(root, dirs, files)
 
@@ -92,36 +138,113 @@ class DvcIgnoreFilter(object):
 
 
 class CleanTree(BaseTree):
-    def __init__(self, tree):
+    def __init__(self, tree, tree_root=None):
         self.tree = tree
+        if tree_root:
+            self._tree_root = tree_root
+        else:
+            self._tree_root = self.tree.tree_root
 
     @cached_property
     def dvcignore(self):
-        return DvcIgnoreFilter(self.tree)
+        return DvcIgnoreFilter(self.tree, self.tree_root)
 
     @property
     def tree_root(self):
-        return self.tree.tree_root
+        return self._tree_root
 
     def open(self, path, mode="r", encoding="utf-8"):
-        return self.tree.open(path, mode, encoding)
+        if self.isfile(path):
+            return self.tree.open(path, mode, encoding)
+        raise FileNotFoundError
 
     def exists(self, path):
-        return self.tree.exists(path)
+        if self.tree.exists(path) and self._parents_exist(path):
+            if self.tree.isdir(path):
+                return self._valid_dirname(path)
+            return self._valid_filename(path)
+        return False
 
     def isdir(self, path):
-        return self.tree.isdir(path)
+        return (
+            self.tree.isdir(path)
+            and self._parents_exist(path)
+            and self._valid_dirname(path)
+        )
+
+    def _valid_dirname(self, path):
+        path = os.path.abspath(path)
+        if path == self.tree_root:
+            return True
+        dirname, basename = os.path.split(path)
+        dirs, _ = self.dvcignore(dirname, [basename], [])
+        if dirs:
+            return True
+        return False
 
     def isfile(self, path):
-        return self.tree.isfile(path)
+        return (
+            self.tree.isfile(path)
+            and self._parents_exist(path)
+            and self._valid_filename(path)
+        )
 
-    def walk(self, top, topdown=True):
-        for root, dirs, files in self.tree.walk(top, topdown):
-            dirs[:], files[:] = self.dvcignore(root, dirs, files)
+    def _valid_filename(self, path):
+        dirname, basename = os.path.split(os.path.normpath(path))
+        _, files = self.dvcignore(os.path.abspath(dirname), [], [basename])
+        if files:
+            return True
+        return False
+
+    def isexec(self, path):
+        return self.exists(path) and self.tree.isexec(path)
+
+    def _parents_exist(self, path):
+        from dvc.repo import Repo
+
+        path = PathInfo(path)
+
+        # if parent is tree_root or inside a .dvc dir we can skip this check
+        if path.parent == self.tree_root or Repo.DVC_DIR in path.parts:
+            return True
+
+        # paths outside of the CleanTree root should be ignored
+        path = relpath(path, self.tree_root)
+        if path.startswith("..") or (
+            os.name == "nt"
+            and not os.path.commonprefix(
+                [os.path.abspath(path), self.tree_root]
+            )
+        ):
+            return False
+
+        # check if parent directories are in our ignores, starting from
+        # tree_root
+        for parent_dir in reversed(PathInfo(path).parents):
+            dirname, basename = os.path.split(parent_dir)
+            if basename == ".":
+                # parent_dir == tree_root
+                continue
+            dirs, _ = self.dvcignore(os.path.abspath(dirname), [basename], [])
+            if not dirs:
+                return False
+        return True
+
+    def walk(self, top, topdown=True, onerror=None):
+        for root, dirs, files in self.tree.walk(
+            top, topdown=topdown, onerror=onerror
+        ):
+            dirs[:], files[:] = self.dvcignore(
+                os.path.abspath(root), dirs, files
+            )
 
             yield root, dirs, files
 
-    def walk_files(self, top):
-        for root, _, files in self.walk(top):
-            for file in files:
-                yield os.path.join(root, file)
+    def stat(self, path):
+        if self.exists(path):
+            return self.tree.stat(path)
+        raise FileNotFoundError
+
+    @property
+    def hash_jobs(self):
+        return self.tree.hash_jobs

dvc/istextfile.py

@@ -7,13 +7,17 @@
 TEXT_CHARS = bytes(range(32, 127)) + b"\n\r\t\f\b"
 
 
-def istextfile(fname, blocksize=512):
+def istextfile(fname, blocksize=512, tree=None):
     """ Uses heuristics to guess whether the given file is text or binary,
         by reading a single block of bytes from the file.
         If more than 30% of the chars in the block are non-text, or there
         are NUL ('\x00') bytes in the block, assume this is a binary file.
     """
-    with open(fname, "rb") as fobj:
+    if tree:
+        open_func = tree.open
+    else:
+        open_func = open
+    with open_func(fname, "rb") as fobj:
         block = fobj.read(blocksize)
 
     if not block:

dvc/lock.py

@@ -5,19 +5,19 @@ import os
 import time
 from datetime import timedelta
 
-import zc.lockfile
 import flufl.lock
+import zc.lockfile
 
 from dvc.exceptions import DvcException
-from dvc.utils import format_link
 from dvc.progress import Tqdm
+from dvc.utils import format_link
 
 DEFAULT_TIMEOUT = 5
 
 FAILED_TO_LOCK_MESSAGE = (
     "cannot perform the command because another DVC process seems to be "
     "running on this project. If that is not the case, manually remove "
-    "`.dvc/lock` and try again."
+    "`.dvc/tmp/lock` and try again."
 )
 
 
@@ -25,7 +25,7 @@ class LockError(DvcException):
     """Thrown when unable to acquire the lock for DVC repo."""
 
 
-class Lock(object):
+class Lock:
     """Class for DVC repo lock.
 
     Uses zc.lockfile as backend.
@@ -47,7 +47,7 @@ class Lock(object):
                 disable=not self._friendly,
                 desc=(
                     "If DVC froze, see `hardlink_lock` in {}".format(
-                        format_link("man.dvc.org/config#core")
+                        format_link("https://man.dvc.org/config#core")
                     )
                 ),
             ):
@@ -88,7 +88,9 @@ class HardlinkLock(flufl.lock.Lock):
         tmp_dir (str): a directory to store claim files.
     """
 
-    def __init__(self, lockfile, tmp_dir=None, **kwargs):
+    def __init__(
+        self, lockfile, tmp_dir=None, **kwargs
+    ):  # pylint: disable=super-init-not-called
         import socket
 
         self._tmp_dir = tmp_dir
@@ -117,7 +119,7 @@ class HardlinkLock(flufl.lock.Lock):
     def lockfile(self):
         return self._lockfile
 
-    def lock(self):
+    def lock(self):  # pylint: disable=arguments-differ
         try:
             super().lock(timedelta(seconds=DEFAULT_TIMEOUT))
         except flufl.lock.TimeOutError:

dvc/logger.py

@@ -7,7 +7,6 @@ import colorama
 
 from dvc.progress import Tqdm
 
-
 FOOTER = (
     "\n{yellow}Having any troubles?{nc}"
     " Hit us up at {blue}https://dvc.org/support{nc},"
@@ -19,20 +18,46 @@ FOOTER = (
 )
 
 
+def addLoggingLevel(levelName, levelNum, methodName=None):
+    """
+    Adds a new logging level to the `logging` module and the
+    currently configured logging class.
+
+    Based on https://stackoverflow.com/questions/2183233
+    """
+    if methodName is None:
+        methodName = levelName.lower()
+
+    assert not hasattr(logging, levelName)
+    assert not hasattr(logging, methodName)
+    assert not hasattr(logging.getLoggerClass(), methodName)
+
+    def logForLevel(self, message, *args, **kwargs):
+        if self.isEnabledFor(levelNum):
+            # pylint: disable=protected-access
+            self._log(levelNum, message, args, **kwargs)
+
+    def logToRoot(message, *args, **kwargs):
+        logging.log(levelNum, message, *args, **kwargs)
+
+    logging.addLevelName(levelNum, levelName)
+    setattr(logging, levelName, levelNum)
+    setattr(logging.getLoggerClass(), methodName, logForLevel)
+    setattr(logging, methodName, logToRoot)
+
+
 class LoggingException(Exception):
     def __init__(self, record):
         msg = "failed to log {}".format(str(record))
         super().__init__(msg)
 
 
-class ExcludeErrorsFilter(logging.Filter):
-    def filter(self, record):
-        return record.levelno < logging.WARNING
+def excludeFilter(level):
+    class ExcludeLevelFilter(logging.Filter):
+        def filter(self, record):
+            return record.levelno < level
 
-
-class ExcludeInfoFilter(logging.Filter):
-    def filter(self, record):
-        return record.levelno < logging.INFO
+    return ExcludeLevelFilter
 
 
 class ColorFormatter(logging.Formatter):
@@ -48,6 +73,7 @@ class ColorFormatter(logging.Formatter):
     """
 
     color_code = {
+        "TRACE": colorama.Fore.GREEN,
         "DEBUG": colorama.Fore.BLUE,
         "WARNING": colorama.Fore.YELLOW,
         "ERROR": colorama.Fore.RED,
@@ -55,7 +81,8 @@ class ColorFormatter(logging.Formatter):
     }
 
     def format(self, record):
-        msg = record.msg.format(*record.args) if record.args else record.msg
+        record.message = record.getMessage()
+        msg = self.formatMessage(record)
 
         if record.levelname == "INFO":
             return msg
@@ -111,12 +138,16 @@ class LoggerHandler(logging.StreamHandler):
             self.flush()
         except RecursionError:
             raise
-        except Exception:
+        except Exception:  # noqa, pylint: disable=broad-except
             self.handleError(record)
 
 
 def _is_verbose():
-    return logging.getLogger("dvc").getEffectiveLevel() == logging.DEBUG
+    return (
+        logging.NOTSET
+        < logging.getLogger("dvc").getEffectiveLevel()
+        <= logging.DEBUG
+    )
 
 
 def _iter_causes(exc):
@@ -141,15 +172,25 @@ def _stack_trace(exc_info):
     )
 
 
+def disable_other_loggers():
+    logging.captureWarnings(True)
+    root = logging.root
+    for (logger_name, logger) in root.manager.loggerDict.items():
+        if logger_name != "dvc" and not logger_name.startswith("dvc."):
+            logger.disabled = True
+
+
 def setup(level=logging.INFO):
     colorama.init()
 
+    addLoggingLevel("TRACE", logging.DEBUG - 5)
     logging.config.dictConfig(
         {
             "version": 1,
             "filters": {
-                "exclude_errors": {"()": ExcludeErrorsFilter},
-                "exclude_info": {"()": ExcludeInfoFilter},
+                "exclude_errors": {"()": excludeFilter(logging.WARNING)},
+                "exclude_info": {"()": excludeFilter(logging.INFO)},
+                "exclude_debug": {"()": excludeFilter(logging.DEBUG)},
             },
             "formatters": {"color": {"()": ColorFormatter}},
             "handlers": {
@@ -167,6 +208,13 @@ def setup(level=logging.INFO):
                     "stream": "ext://sys.stdout",
                     "filters": ["exclude_info"],
                 },
+                "console_trace": {
+                    "class": "dvc.logger.LoggerHandler",
+                    "level": "TRACE",
+                    "formatter": "color",
+                    "stream": "ext://sys.stdout",
+                    "filters": ["exclude_debug"],
+                },
                 "console_errors": {
                     "class": "dvc.logger.LoggerHandler",
                     "level": "WARNING",
@@ -180,25 +228,11 @@ def setup(level=logging.INFO):
                     "handlers": [
                         "console_info",
                         "console_debug",
-                        "console_errors",
-                    ],
-                },
-                "paramiko": {
-                    "level": logging.CRITICAL,
-                    "handlers": [
-                        "console_info",
-                        "console_debug",
-                        "console_errors",
-                    ],
-                },
-                "flufl.lock": {
-                    "level": logging.CRITICAL,
-                    "handlers": [
-                        "console_info",
-                        "console_debug",
+                        "console_trace",
                         "console_errors",
                     ],
                 },
             },
+            "disable_existing_loggers": False,
         }
     )

dvc/main.py

@@ -6,12 +6,11 @@ import logging
 from dvc import analytics
 from dvc.cli import parse_args
 from dvc.config import ConfigError
-from dvc.exceptions import DvcParserError
-from dvc.exceptions import NotDvcRepoError
+from dvc.exceptions import DvcException, DvcParserError, NotDvcRepoError
 from dvc.external_repo import clean_repos
-from dvc.logger import FOOTER
-from dvc.utils import format_link
+from dvc.logger import FOOTER, disable_other_loggers
 from dvc.remote.pool import close_pools
+from dvc.utils import format_link
 
 # Workaround for CPython bug. See [1] and [2] for more info.
 # [1] https://github.com/aws/aws-cli/blob/1.16.277/awscli/clidriver.py#L55
@@ -19,7 +18,6 @@ from dvc.remote.pool import close_pools
 
 "".encode("idna")
 
-
 logger = logging.getLogger("dvc")
 
 
@@ -33,17 +31,23 @@ def main(argv=None):
         int: command's return code.
     """
     args = None
-    cmd = None
+    disable_other_loggers()
 
     outerLogLevel = logger.level
     try:
         args = parse_args(argv)
 
-        if args.quiet:
-            logger.setLevel(logging.CRITICAL)
-
-        elif args.verbose:
-            logger.setLevel(logging.DEBUG)
+        verbosity = args.verbose - args.quiet
+        if verbosity:
+            logger.setLevel(
+                {
+                    -2: logging.CRITICAL,
+                    -1: logging.ERROR,
+                    1: logging.DEBUG,
+                    2: logging.TRACE,
+                }[max(-2, min(verbosity, 2))]
+            )
+        logger.trace(args)
 
         cmd = args.func(args)
         ret = cmd.run()
@@ -58,8 +62,11 @@ def main(argv=None):
         ret = 253
     except DvcParserError:
         ret = 254
-    except Exception as exc:  # pylint: disable=broad-except
-        if isinstance(exc, OSError) and exc.errno == errno.EMFILE:
+    except DvcException:
+        ret = 255
+        logger.exception("")
+    except OSError as exc:
+        if exc.errno == errno.EMFILE:
             logger.exception(
                 "too many open files, please visit "
                 "{} to see how to handle this "
@@ -71,10 +78,13 @@ def main(argv=None):
         else:
             logger.exception("unexpected error")
         ret = 255
+    except Exception:  # noqa, pylint: disable=broad-except
+        logger.exception("unexpected error")
+        ret = 255
     finally:
         logger.setLevel(outerLogLevel)
 
-        # Closing pools by-hand to prevent wierd messages when closing SSH
+        # Closing pools by-hand to prevent weird messages when closing SSH
         # connections. See https://github.com/iterative/dvc/issues/3248 for
         # more info.
         close_pools()

dvc/output/__init__.py

@@ -1,32 +1,35 @@
+from collections import defaultdict
 from urllib.parse import urlparse
-from voluptuous import Any, Required, Lower, Length, Coerce, And, SetTo
 
-from dvc.output.base import OutputBase
-from dvc.output.gs import OutputGS
-from dvc.output.hdfs import OutputHDFS
-from dvc.output.local import OutputLOCAL
-from dvc.output.s3 import OutputS3
-from dvc.output.ssh import OutputSSH
-from dvc.remote import Remote
-from dvc.remote.hdfs import RemoteHDFS
-from dvc.remote.local import RemoteLOCAL
-from dvc.remote.s3 import RemoteS3
+from funcy import collecting, project
+from voluptuous import And, Any, Coerce, Length, Lower, Required, SetTo
+
+from dvc.output.base import BaseOutput
+from dvc.output.gs import GSOutput
+from dvc.output.hdfs import HDFSOutput
+from dvc.output.local import LocalOutput
+from dvc.output.s3 import S3Output
+from dvc.output.ssh import SSHOutput
+from dvc.remote import get_remote
+from dvc.remote.hdfs import HDFSRemoteTree
+from dvc.remote.local import LocalRemoteTree
+from dvc.remote.s3 import S3RemoteTree
 from dvc.scheme import Schemes
 
 OUTS = [
-    OutputHDFS,
-    OutputS3,
-    OutputGS,
-    OutputSSH,
-    # NOTE: OutputLOCAL is the default choice
+    HDFSOutput,
+    S3Output,
+    GSOutput,
+    SSHOutput,
+    # NOTE: LocalOutput is the default choice
 ]
 
 OUTS_MAP = {
-    Schemes.HDFS: OutputHDFS,
-    Schemes.S3: OutputS3,
-    Schemes.GS: OutputGS,
-    Schemes.SSH: OutputSSH,
-    Schemes.LOCAL: OutputLOCAL,
+    Schemes.HDFS: HDFSOutput,
+    Schemes.S3: S3Output,
+    Schemes.GS: GSOutput,
+    Schemes.SSH: SSHOutput,
+    Schemes.LOCAL: LocalOutput,
 }
 
 CHECKSUM_SCHEMA = Any(
@@ -44,26 +47,26 @@ CHECKSUM_SCHEMA = Any(
 # so when a few types of outputs share the same name, we only need
 # specify it once.
 CHECKSUMS_SCHEMA = {
-    RemoteLOCAL.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
-    RemoteS3.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
-    RemoteHDFS.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
+    LocalRemoteTree.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
+    S3RemoteTree.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
+    HDFSRemoteTree.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
 }
 
-TAGS_SCHEMA = {str: CHECKSUMS_SCHEMA}
-
 SCHEMA = CHECKSUMS_SCHEMA.copy()
-SCHEMA[Required(OutputBase.PARAM_PATH)] = str
-SCHEMA[OutputBase.PARAM_CACHE] = bool
-SCHEMA[OutputBase.PARAM_METRIC] = OutputBase.METRIC_SCHEMA
-SCHEMA[OutputBase.PARAM_TAGS] = TAGS_SCHEMA
-SCHEMA[OutputBase.PARAM_PERSIST] = bool
+SCHEMA[Required(BaseOutput.PARAM_PATH)] = str
+SCHEMA[BaseOutput.PARAM_CACHE] = bool
+SCHEMA[BaseOutput.PARAM_METRIC] = BaseOutput.METRIC_SCHEMA
+SCHEMA[BaseOutput.PARAM_PLOT] = bool
+SCHEMA[BaseOutput.PARAM_PERSIST] = bool
 
 
-def _get(stage, p, info, cache, metric, persist=False, tags=None):
+def _get(
+    stage, p, info=None, cache=True, metric=False, plot=False, persist=False
+):
     parsed = urlparse(p)
 
     if parsed.scheme == "remote":
-        remote = Remote(stage.repo, name=parsed.netloc)
+        remote = get_remote(stage.repo, name=parsed.netloc)
         return OUTS_MAP[remote.scheme](
             stage,
             p,
@@ -71,8 +74,8 @@ def _get(stage, p, info, cache, metric, persist=False, tags=None):
             cache=cache,
             remote=remote,
             metric=metric,
+            plot=plot,
             persist=persist,
-            tags=tags,
         )
 
     for o in OUTS:
@@ -84,29 +87,29 @@ def _get(stage, p, info, cache, metric, persist=False, tags=None):
                 cache=cache,
                 remote=None,
                 metric=metric,
+                plot=plot,
                 persist=persist,
-                tags=tags,
             )
-    return OutputLOCAL(
+    return LocalOutput(
         stage,
         p,
         info,
         cache=cache,
         remote=None,
         metric=metric,
+        plot=plot,
         persist=persist,
-        tags=tags,
     )
 
 
 def loadd_from(stage, d_list):
     ret = []
     for d in d_list:
-        p = d.pop(OutputBase.PARAM_PATH)
-        cache = d.pop(OutputBase.PARAM_CACHE, True)
-        metric = d.pop(OutputBase.PARAM_METRIC, False)
-        persist = d.pop(OutputBase.PARAM_PERSIST, False)
-        tags = d.pop(OutputBase.PARAM_TAGS, None)
+        p = d.pop(BaseOutput.PARAM_PATH)
+        cache = d.pop(BaseOutput.PARAM_CACHE, True)
+        metric = d.pop(BaseOutput.PARAM_METRIC, False)
+        plot = d.pop(BaseOutput.PARAM_PLOT, False)
+        persist = d.pop(BaseOutput.PARAM_PERSIST, False)
         ret.append(
             _get(
                 stage,
@@ -114,24 +117,67 @@ def loadd_from(stage, d_list):
                 info=d,
                 cache=cache,
                 metric=metric,
+                plot=plot,
                 persist=persist,
-                tags=tags,
             )
         )
     return ret
 
 
-def loads_from(stage, s_list, use_cache=True, metric=False, persist=False):
-    ret = []
-    for s in s_list:
-        ret.append(
-            _get(
-                stage,
-                s,
-                info={},
-                cache=use_cache,
-                metric=metric,
-                persist=persist,
-            )
+def loads_from(
+    stage, s_list, use_cache=True, metric=False, plot=False, persist=False
+):
+    return [
+        _get(
+            stage,
+            s,
+            info={},
+            cache=use_cache,
+            metric=metric,
+            plot=plot,
+            persist=persist,
         )
-    return ret
+        for s in s_list
+    ]
+
+
+def _split_dict(d, keys):
+    return project(d, keys), project(d, d.keys() - keys)
+
+
+def _merge_data(s_list):
+    d = defaultdict(dict)
+    for key in s_list:
+        if isinstance(key, str):
+            d[key].update({})
+            continue
+        if not isinstance(key, dict):
+            raise ValueError(f"'{type(key).__name__}' not supported.")
+
+        for k, flags in key.items():
+            if not isinstance(flags, dict):
+                raise ValueError(
+                    f"Expected dict for '{k}', got: '{type(flags).__name__}'"
+                )
+            d[k].update(flags)
+    return d
+
+
+@collecting
+def load_from_pipeline(stage, s_list, typ="outs"):
+    if typ not in (stage.PARAM_OUTS, stage.PARAM_METRICS, stage.PARAM_PLOTS):
+        raise ValueError(f"'{typ}' key is not allowed for pipeline files.")
+
+    metric = typ == stage.PARAM_METRICS
+    plot = typ == stage.PARAM_PLOTS
+
+    d = _merge_data(s_list)
+
+    for path, flags in d.items():
+        plt_d = {}
+        if plot:
+            from dvc.schema import PLOT_PROPS
+
+            plt_d, flags = _split_dict(flags, keys=PLOT_PROPS.keys())
+        extra = project(flags, ["cache", "persist"])
+        yield _get(stage, path, {}, plot=plt_d or plot, metric=metric, **extra)

dvc/output/base.py

@@ -1,52 +1,68 @@
 import logging
-from urllib.parse import urlparse
+import os
 from copy import copy
+from urllib.parse import urlparse
 
 from voluptuous import Any
 
 import dvc.prompt as prompt
 from dvc.cache import NamedCache
-from dvc.exceptions import CollectCacheError, RemoteCacheRequiredError
-from dvc.exceptions import DvcException
-from dvc.remote.base import RemoteBASE
-
+from dvc.exceptions import (
+    CollectCacheError,
+    DvcException,
+    RemoteCacheRequiredError,
+)
+from dvc.remote.base import BaseRemoteTree, Remote
 
 logger = logging.getLogger(__name__)
 
 
 class OutputDoesNotExistError(DvcException):
     def __init__(self, path):
-        msg = "output '{}' does not exist".format(path)
+        msg = f"output '{path}' does not exist"
         super().__init__(msg)
 
 
 class OutputIsNotFileOrDirError(DvcException):
     def __init__(self, path):
-        msg = "output '{}' is not a file or directory".format(path)
+        msg = f"output '{path}' is not a file or directory"
         super().__init__(msg)
 
 
 class OutputAlreadyTrackedError(DvcException):
     def __init__(self, path):
-        msg = "output '{}' is already tracked by scm (e.g. git)".format(path)
+        msg = f""" output '{path}' is already tracked by SCM (e.g. Git).
+    You can remove it from Git, then add to DVC.
+        To stop tracking from Git:
+            git rm -r --cached '{path}'
+            git commit -m "stop tracking {path}" """
         super().__init__(msg)
 
 
 class OutputIsStageFileError(DvcException):
     def __init__(self, path):
-        super().__init__("Stage file '{}' cannot be an output.".format(path))
+        super().__init__(f"Stage file '{path}' cannot be an output.")
 
 
-class OutputBase(object):
+class BaseOutput:
     IS_DEPENDENCY = False
 
-    REMOTE = RemoteBASE
+    REMOTE_CLS = Remote
+    TREE_CLS = BaseRemoteTree
 
     PARAM_PATH = "path"
     PARAM_CACHE = "cache"
     PARAM_METRIC = "metric"
     PARAM_METRIC_TYPE = "type"
     PARAM_METRIC_XPATH = "xpath"
+    PARAM_PLOT = "plot"
+    PARAM_PLOT_TEMPLATE = "template"
+    PARAM_PLOT_X = "x"
+    PARAM_PLOT_Y = "y"
+    PARAM_PLOT_X_LABEL = "x_label"
+    PARAM_PLOT_Y_LABEL = "y_label"
+    PARAM_PLOT_TITLE = "title"
+    PARAM_PLOT_HEADER = "header"
     PARAM_PERSIST = "persist"
 
     METRIC_SCHEMA = Any(
@@ -58,8 +74,6 @@ class OutputBase(object):
         },
     )
 
-    PARAM_TAGS = "tags"
-
     DoesNotExistError = OutputDoesNotExistError
     IsNotFileOrDirError = OutputIsNotFileOrDirError
     IsStageFileError = OutputIsStageFileError
@@ -74,8 +88,8 @@ class OutputBase(object):
         remote=None,
         cache=True,
         metric=False,
+        plot=False,
         persist=False,
-        tags=None,
     ):
         self._validate_output_path(path)
         # This output (and dependency) objects have too many paths/urls
@@ -92,11 +106,15 @@ class OutputBase(object):
         self.repo = stage.repo if stage else None
         self.def_path = path
         self.info = info
-        self.remote = remote or self.REMOTE(self.repo, {})
+        if remote:
+            self.remote = remote
+        else:
+            tree = self.TREE_CLS(self.repo, {})
+            self.remote = self.REMOTE_CLS(tree)
         self.use_cache = False if self.IS_DEPENDENCY else cache
         self.metric = False if self.IS_DEPENDENCY else metric
+        self.plot = False if self.IS_DEPENDENCY else plot
         self.persist = persist
-        self.tags = None if self.IS_DEPENDENCY else (tags or {})
 
         self.path_info = self._parse_path(remote, path)
         if self.use_cache and self.cache is None:
@@ -106,7 +124,7 @@ class OutputBase(object):
         if remote:
             parsed = urlparse(path)
             return remote.path_info / parsed.path.lstrip("/")
-        return self.REMOTE.path_cls(path)
+        return self.TREE_CLS.PATH_CLS(path)
 
     def __repr__(self):
         return "{class_name}: '{def_path}'".format(
@@ -118,7 +136,7 @@ class OutputBase(object):
 
     @property
     def scheme(self):
-        return self.REMOTE.scheme
+        return self.TREE_CLS.scheme
 
     @property
     def is_in_repo(self):
@@ -141,26 +159,40 @@ class OutputBase(object):
 
     @classmethod
     def supported(cls, url):
-        return cls.REMOTE.supported(url)
+        return cls.TREE_CLS.supported(url)
 
     @property
     def cache_path(self):
-        return self.cache.checksum_to_path_info(self.checksum).url
+        return self.cache.hash_to_path_info(self.checksum).url
+
+    @property
+    def checksum_type(self):
+        return self.remote.tree.PARAM_CHECKSUM
 
     @property
     def checksum(self):
-        return self.info.get(self.remote.PARAM_CHECKSUM)
+        return self.info.get(self.remote.tree.PARAM_CHECKSUM)
+
+    @checksum.setter
+    def checksum(self, checksum):
+        self.info[self.remote.tree.PARAM_CHECKSUM] = checksum
+
+    def get_checksum(self):
+        return self.remote.get_hash(self.path_info)
 
     @property
     def is_dir_checksum(self):
-        return self.remote.is_dir_checksum(self.checksum)
+        return self.remote.is_dir_hash(self.checksum)
 
     @property
     def exists(self):
-        return self.remote.exists(self.path_info)
+        return self.remote.tree.exists(self.path_info)
+
+    def save_info(self):
+        return self.remote.save_info(self.path_info)
 
     def changed_checksum(self):
-        return self.checksum != self.remote.get_checksum(self.path_info)
+        return self.checksum != self.get_checksum()
 
     def changed_cache(self, filter_info=None):
         if not self.use_cache or not self.checksum:
@@ -190,13 +222,32 @@ class OutputBase(object):
 
     @property
     def is_empty(self):
-        return self.remote.is_empty(self.path_info)
+        return self.remote.tree.is_empty(self.path_info)
 
     def isdir(self):
-        return self.remote.isdir(self.path_info)
+        return self.remote.tree.isdir(self.path_info)
 
     def isfile(self):
-        return self.remote.isfile(self.path_info)
+        return self.remote.tree.isfile(self.path_info)
+
+    # pylint: disable=no-member
+
+    def ignore(self):
+        if not self.use_scm_ignore:
+            return
+
+        if self.repo.scm.is_tracked(self.fspath):
+            raise OutputAlreadyTrackedError(self)
+
+        self.repo.scm.ignore(self.fspath)
+
+    def ignore_remove(self):
+        if not self.use_scm_ignore:
+            return
+
+        self.repo.scm.ignore_remove(self.fspath)
+
+    # pylint: enable=no-member
 
     def save(self):
         if not self.exists:
@@ -206,39 +257,32 @@ class OutputBase(object):
             raise self.IsNotFileOrDirError(self)
 
         if self.is_empty:
-            logger.warning("'{}' is empty.".format(self))
+            logger.warning(f"'{self}' is empty.")
 
-        if self.use_scm_ignore:
-            if self.repo.scm.is_tracked(self.fspath):
-                raise OutputAlreadyTrackedError(self)
+        self.ignore()
 
-            self.repo.scm.ignore(self.fspath)
+        if self.metric or self.plot:
+            self.verify_metric()
 
         if not self.use_cache:
-            self.info = self.remote.save_info(self.path_info)
-            if self.metric:
-                self.verify_metric()
+            self.info = self.save_info()
             if not self.IS_DEPENDENCY:
-                logger.info(
-                    "Output '{}' doesn't use cache. Skipping saving.".format(
-                        self
-                    )
+                logger.debug(
+                    "Output '%s' doesn't use cache. Skipping saving.", self
                 )
             return
 
         assert not self.IS_DEPENDENCY
 
         if not self.changed():
-            logger.info(
-                "Output '{}' didn't change. Skipping saving.".format(self)
-            )
+            logger.debug("Output '%s' didn't change. Skipping saving.", self)
             return
 
-        self.info = self.remote.save_info(self.path_info)
+        self.info = self.save_info()
 
     def commit(self):
         if self.use_cache:
-            self.cache.save(self.path_info, self.info)
+            self.cache.save(self.path_info, self.cache.tree, self.info)
 
     def dumpd(self):
         ret = copy(self.info)
@@ -247,7 +291,8 @@ class OutputBase(object):
         if self.IS_DEPENDENCY:
             return ret
 
-        ret[self.PARAM_CACHE] = self.use_cache
+        if not self.use_cache:
+            ret[self.PARAM_CACHE] = self.use_cache
 
         if isinstance(self.metric, dict):
             if (
@@ -256,27 +301,27 @@ class OutputBase(object):
             ):
                 del self.metric[self.PARAM_METRIC_XPATH]
 
-        ret[self.PARAM_METRIC] = self.metric
-        ret[self.PARAM_PERSIST] = self.persist
+        if self.metric:
+            ret[self.PARAM_METRIC] = self.metric
 
-        if self.tags:
-            ret[self.PARAM_TAGS] = self.tags
+        if self.plot:
+            ret[self.PARAM_PLOT] = self.plot
+
+        if self.persist:
+            ret[self.PARAM_PERSIST] = self.persist
 
         return ret
 
     def verify_metric(self):
-        raise DvcException(
-            "verify metric is not supported for {}".format(self.scheme)
-        )
+        raise DvcException(f"verify metric is not supported for {self.scheme}")
 
     def download(self, to):
-        self.remote.download(self.path_info, to.path_info)
+        self.remote.tree.download(self.path_info, to.path_info)
 
     def checkout(
         self,
         force=False,
         progress_callback=None,
-        tag=None,
         relink=False,
         filter_info=None,
     ):
@@ -287,14 +332,9 @@ class OutputBase(object):
                 )
             return None
 
-        if tag:
-            info = self.tags[tag]
-        else:
-            info = self.info
-
         return self.cache.checkout(
             self.path_info,
-            info,
+            self.info,
             force=force,
             progress_callback=progress_callback,
             relink=relink,
@@ -302,18 +342,19 @@ class OutputBase(object):
         )
 
     def remove(self, ignore_remove=False):
-        self.remote.remove(self.path_info)
+        self.remote.tree.remove(self.path_info)
         if self.scheme != "local":
             return
 
-        if ignore_remove and self.use_scm_ignore:
-            self.repo.scm.ignore_remove(self.fspath)
+        if ignore_remove:
+            self.ignore_remove()
 
     def move(self, out):
+        # pylint: disable=no-member
         if self.scheme == "local" and self.use_scm_ignore:
             self.repo.scm.ignore_remove(self.fspath)
 
-        self.remote.move(self.path_info, out.path_info)
+        self.remote.tree.move(self.path_info, out.path_info)
         self.def_path = out.def_path
         self.path_info = out.path_info
         self.save()
@@ -332,9 +373,20 @@ class OutputBase(object):
 
     def unprotect(self):
         if self.exists:
-            self.remote.unprotect(self.path_info)
+            self.remote.tree.unprotect(self.path_info)
 
-    def _collect_used_dir_cache(
+    def get_dir_cache(self, **kwargs):
+        if not self.is_dir_checksum:
+            raise DvcException("cannot get dir cache for file checksum")
+        if self.cache.changed_cache_file(self.checksum):
+            self.repo.cloud.pull(
+                NamedCache.make("local", self.checksum, str(self)),
+                show_checksums=False,
+                **kwargs,
+            )
+        return self.dir_cache
+
+    def collect_used_dir_cache(
         self, remote=None, force=False, jobs=None, filter_info=None
     ):
         """Get a list of `info`s related to the given directory.
@@ -358,16 +410,10 @@ class OutputBase(object):
 
         cache = NamedCache()
 
-        if self.cache.changed_cache_file(self.checksum):
-            try:
-                self.repo.cloud.pull(
-                    NamedCache.make("local", self.checksum, str(self)),
-                    jobs=jobs,
-                    remote=remote,
-                    show_checksums=False,
-                )
-            except DvcException:
-                logger.debug("failed to pull cache for '{}'".format(self))
+        try:
+            self.get_dir_cache(jobs=jobs, remote=remote)
+        except DvcException:
+            logger.debug(f"failed to pull cache for '{self}'")
 
         if self.cache.changed_cache_file(self.checksum):
             msg = (
@@ -383,11 +429,21 @@ class OutputBase(object):
             else:
                 return cache
 
+        path = str(self.path_info)
+        filter_path = str(filter_info) if filter_info else None
+        is_win = os.name == "nt"
         for entry in self.dir_cache:
-            checksum = entry[self.remote.PARAM_CHECKSUM]
-            info = self.path_info / entry[self.remote.PARAM_RELPATH]
-            if not filter_info or info.isin_or_eq(filter_info):
-                cache.add(self.scheme, checksum, str(info))
+            checksum = entry[self.remote.tree.PARAM_CHECKSUM]
+            entry_relpath = entry[self.remote.tree.PARAM_RELPATH]
+            if is_win:
+                entry_relpath = entry_relpath.replace("/", os.sep)
+            entry_path = os.path.join(path, entry_relpath)
+            if (
+                not filter_path
+                or entry_path == filter_path
+                or entry_path.startswith(filter_path + os.sep)
+            ):
+                cache.add(self.scheme, checksum, entry_path)
 
         return cache
 
@@ -409,12 +465,23 @@ class OutputBase(object):
             cache.external[dep.repo_pair].add(dep.def_path)
             return cache
 
-        if not self.info:
-            logger.warning(
-                "Output '{}'({}) is missing version info. Cache for it will "
-                "not be collected. Use `dvc repro` to get your pipeline up to "
-                "date.".format(self, self.stage)
+        if not self.checksum:
+            msg = (
+                "Output '{}'({}) is missing version info. "
+                "Cache for it will not be collected. "
+                "Use `dvc repro` to get your pipeline up to date.".format(
+                    self, self.stage
+                )
             )
+            if self.exists:
+                msg += (
+                    "\n"
+                    "You can also use `dvc commit {stage.addressing}` "
+                    "to associate existing '{out}' with {stage}.".format(
+                        out=self, stage=self.stage
+                    )
+                )
+            logger.warning(msg)
             return NamedCache()
 
         ret = NamedCache.make(self.scheme, self.checksum, str(self))
@@ -422,13 +489,15 @@ class OutputBase(object):
         if not self.is_dir_checksum:
             return ret
 
-        ret.update(self._collect_used_dir_cache(**kwargs))
+        ret.add_child_cache(
+            self.checksum, self.collect_used_dir_cache(**kwargs),
+        )
 
         return ret
 
     @classmethod
     def _validate_output_path(cls, path):
-        from dvc.stage import Stage
+        from dvc.dvcfile import is_valid_filename
 
-        if Stage.is_valid_filename(path):
+        if is_valid_filename(path):
             raise cls.IsStageFileError(path)

dvc/output/gs.py

@@ -1,6 +1,6 @@
-from dvc.output.s3 import OutputS3
-from dvc.remote.gs import RemoteGS
+from dvc.output.s3 import S3Output
+from dvc.remote.gs import GSRemoteTree
 
 
-class OutputGS(OutputS3):
-    REMOTE = RemoteGS
+class GSOutput(S3Output):
+    TREE_CLS = GSRemoteTree

dvc/output/hdfs.py

@@ -1,6 +1,6 @@
-from dvc.output.base import OutputBase
-from dvc.remote.hdfs import RemoteHDFS
+from dvc.output.base import BaseOutput
+from dvc.remote.hdfs import HDFSRemoteTree
 
 
-class OutputHDFS(OutputBase):
-    REMOTE = RemoteHDFS
+class HDFSOutput(BaseOutput):
+    TREE_CLS = HDFSRemoteTree

dvc/output/local.py

@@ -4,18 +4,17 @@ from urllib.parse import urlparse
 
 from dvc.exceptions import DvcException
 from dvc.istextfile import istextfile
-from dvc.output.base import OutputBase
-from dvc.remote.local import RemoteLOCAL
+from dvc.output.base import BaseOutput
+from dvc.remote.local import LocalRemote, LocalRemoteTree
 from dvc.utils import relpath
-from dvc.compat import fspath_py35
 from dvc.utils.fs import path_isin
 
-
 logger = logging.getLogger(__name__)
 
 
-class OutputLOCAL(OutputBase):
-    REMOTE = RemoteLOCAL
+class LocalOutput(BaseOutput):
+    REMOTE_CLS = LocalRemote
+    TREE_CLS = LocalRemoteTree
     sep = os.sep
 
     def __init__(self, stage, path, *args, **kwargs):
@@ -35,15 +34,15 @@ class OutputLOCAL(OutputBase):
             #
             # FIXME: if we have Windows path containing / or posix one with \
             # then we have #2059 bug and can't really handle that.
-            p = self.REMOTE.path_cls(path)
-            if not p.is_absolute():
+            p = self.TREE_CLS.PATH_CLS(path)
+            if self.stage and not p.is_absolute():
                 p = self.stage.wdir / p
 
-        abs_p = os.path.abspath(os.path.normpath(fspath_py35(p)))
-        return self.REMOTE.path_cls(abs_p)
+        abs_p = os.path.abspath(os.path.normpath(p))
+        return self.TREE_CLS.PATH_CLS(abs_p)
 
     def __str__(self):
-        if not self.is_in_repo:
+        if not self.repo or not self.is_in_repo:
             return str(self.def_path)
 
         cur_dir = os.getcwd()
@@ -73,17 +72,18 @@ class OutputLOCAL(OutputBase):
         return ret
 
     def verify_metric(self):
-        if not self.metric:
+        if not self.metric or self.plot:
             return
 
-        path = fspath_py35(self.path_info)
+        path = os.fspath(self.path_info)
         if not os.path.exists(path):
             return
 
+        name = "metrics" if self.metric else "plot"
         if os.path.isdir(path):
-            msg = "directory '{}' cannot be used as metrics."
-            raise DvcException(msg.format(self.path_info))
+            msg = "directory '{}' cannot be used as {}."
+            raise IsADirectoryError(msg.format(self.path_info, name))
 
         if not istextfile(path):
-            msg = "binary file '{}' cannot be used as metrics."
-            raise DvcException(msg.format(self.path_info))
+            msg = "binary file '{}' cannot be used as {}."
+            raise DvcException(msg.format(self.path_info, name))

dvc/output/s3.py

@@ -1,6 +1,6 @@
-from dvc.output.base import OutputBase
-from dvc.remote.s3 import RemoteS3
+from dvc.output.base import BaseOutput
+from dvc.remote.s3 import S3RemoteTree
 
 
-class OutputS3(OutputBase):
-    REMOTE = RemoteS3
+class S3Output(BaseOutput):
+    TREE_CLS = S3RemoteTree

dvc/output/ssh.py

@@ -1,6 +1,7 @@
-from dvc.output.base import OutputBase
-from dvc.remote.ssh import RemoteSSH
+from dvc.output.base import BaseOutput
+from dvc.remote.ssh import SSHRemote, SSHRemoteTree
 
 
-class OutputSSH(OutputBase):
-    REMOTE = RemoteSSH
+class SSHOutput(BaseOutput):
+    REMOTE_CLS = SSHRemote
+    TREE_CLS = SSHRemoteTree

dvc/path_info.py

@@ -1,6 +1,7 @@
+# pylint: disable=protected-access
 import os
-import posixpath
 import pathlib
+import posixpath
 from urllib.parse import urlparse
 
 from funcy import cached_property
@@ -8,7 +9,7 @@ from funcy import cached_property
 from dvc.utils import relpath
 
 
-class _BasePath(object):
+class _BasePath:
     def overlaps(self, other):
         if isinstance(other, (str, bytes)):
             other = self.__class__(other)
@@ -17,7 +18,7 @@ class _BasePath(object):
         return self.isin_or_eq(other) or other.isin(self)
 
     def isin_or_eq(self, other):
-        return self == other or self.isin(other)
+        return self == other or self.isin(other)  # pylint: disable=no-member
 
 
 class PathInfo(pathlib.PurePath, _BasePath):
@@ -30,15 +31,14 @@ class PathInfo(pathlib.PurePath, _BasePath):
     def __new__(cls, *args):
         # Construct a proper subclass depending on current os
         if cls is PathInfo:
-            cls = WindowsPathInfo if os.name == "nt" else PosixPathInfo
+            cls = (  # pylint: disable=self-cls-assignment
+                WindowsPathInfo if os.name == "nt" else PosixPathInfo
+            )
+
         return cls._from_parts(args)
 
-    @classmethod
-    def from_posix(cls, s):
-        return cls(PosixPathInfo(s))
-
     def as_posix(self):
-        f = self._flavour
+        f = self._flavour  # pylint: disable=no-member
         # Unlike original implementation [1] that uses `str()` we actually need
         # to use `fspath`, because we've overridden `__str__` method to return
         # relative paths, which will break original `as_posix`.
@@ -54,7 +54,6 @@ class PathInfo(pathlib.PurePath, _BasePath):
         return "{}: '{}'".format(type(self).__name__, self)
 
     # This permits passing it to file utils directly in Python 3.6+
-    # With Python 2.7, Python 3.5+ we are stuck with path_info.fspath for now
     def __fspath__(self):
         return pathlib.PurePath.__str__(self)
 
@@ -92,7 +91,7 @@ class _URLPathInfo(PosixPathInfo):
     __unicode__ = __str__
 
 
-class _URLPathParents(object):
+class _URLPathParents:
     def __init__(self, src):
         self.src = src
         self._parents = self.src._path.parents
@@ -104,7 +103,7 @@ class _URLPathParents(object):
         return self.src.replace(path=self._parents[idx])
 
     def __repr__(self):
-        return "<{}.parents>".format(self.src)
+        return f"<{self.src}.parents>"
 
 
 class URLInfo(_BasePath):
@@ -115,7 +114,7 @@ class URLInfo(_BasePath):
         assert not p.query and not p.params and not p.fragment
         assert p.password is None
 
-        self.fill_parts(p.scheme, p.hostname, p.username, p.port, p.path)
+        self._fill_parts(p.scheme, p.hostname, p.username, p.port, p.path)
 
     @classmethod
     def from_parts(
@@ -124,13 +123,13 @@ class URLInfo(_BasePath):
         assert bool(host) ^ bool(netloc)
 
         if netloc is not None:
-            return cls("{}://{}{}".format(scheme, netloc, path))
+            return cls(f"{scheme}://{netloc}{path}")
 
         obj = cls.__new__(cls)
-        obj.fill_parts(scheme, host, user, port, path)
+        obj._fill_parts(scheme, host, user, port, path)
         return obj
 
-    def fill_parts(self, scheme, host, user, port, path):
+    def _fill_parts(self, scheme, host, user, port, path):
         assert scheme != "remote"
         assert isinstance(path, (str, bytes, _URLPathInfo))
 
@@ -158,7 +157,7 @@ class URLInfo(_BasePath):
 
     @cached_property
     def url(self):
-        return "{}://{}{}".format(self.scheme, self.netloc, self._spath)
+        return f"{self.scheme}://{self.netloc}{self._spath}"
 
     def __str__(self):
         return self.url
@@ -220,10 +219,10 @@ class URLInfo(_BasePath):
         if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         if self.__class__ != other.__class__:
-            msg = "'{}' has incompatible class with '{}'".format(self, other)
+            msg = f"'{self}' has incompatible class with '{other}'"
             raise ValueError(msg)
         if self._base_parts != other._base_parts:
-            msg = "'{}' does not start with '{}'".format(self, other)
+            msg = f"'{self}' does not start with '{other}'"
             raise ValueError(msg)
         return self._path.relative_to(other._path)
 
@@ -241,3 +240,78 @@ class CloudURLInfo(URLInfo):
     @property
     def path(self):
         return self._spath.lstrip("/")
+
+
+class HTTPURLInfo(URLInfo):
+    __hash__ = URLInfo.__hash__
+
+    def __init__(self, url):
+        p = urlparse(url)
+        stripped = p._replace(params=None, query=None, fragment=None)
+        super().__init__(stripped.geturl())
+        self.params = p.params
+        self.query = p.query
+        self.fragment = p.fragment
+
+    @classmethod
+    def from_parts(
+        cls,
+        scheme=None,
+        host=None,
+        user=None,
+        port=None,
+        path="",
+        netloc=None,
+        params=None,
+        query=None,
+        fragment=None,
+    ):  # pylint: disable=arguments-differ
+        assert bool(host) ^ bool(netloc)
+
+        if netloc is not None:
+            return cls(
+                "{}://{}{}{}{}{}".format(
+                    scheme,
+                    netloc,
+                    path,
+                    (";" + params) if params else "",
+                    ("?" + query) if query else "",
+                    ("#" + fragment) if fragment else "",
+                )
+            )
+
+        obj = cls.__new__(cls)
+        obj._fill_parts(scheme, host, user, port, path)
+        obj.params = params
+        obj.query = query
+        obj.fragment = fragment
+        return obj
+
+    @property
+    def _extra_parts(self):
+        return (self.params, self.query, self.fragment)
+
+    @property
+    def parts(self):
+        return self._base_parts + self._path.parts + self._extra_parts
+
+    @cached_property
+    def url(self):
+        return "{}://{}{}{}{}{}".format(
+            self.scheme,
+            self.netloc,
+            self._spath,
+            (";" + self.params) if self.params else "",
+            ("?" + self.query) if self.query else "",
+            ("#" + self.fragment) if self.fragment else "",
+        )
+
+    def __eq__(self, other):
+        if isinstance(other, (str, bytes)):
+            other = self.__class__(other)
+        return (
+            self.__class__ == other.__class__
+            and self._base_parts == other._base_parts
+            and self._path == other._path
+            and self._extra_parts == other._extra_parts
+        )

dvc/progress.py

@@ -19,18 +19,17 @@ class Tqdm(tqdm):
 
     BAR_FMT_DEFAULT = (
         "{percentage:3.0f}% {desc}|{bar}|"
-        "{n_fmt}/{total_fmt}"
-        " [{elapsed}<{remaining}, {rate_fmt:>11}{postfix}]"
+        "{postfix[info]}{n_fmt}/{total_fmt}"
+        " [{elapsed}<{remaining}, {rate_fmt:>11}]"
     )
     # nested bars should have fixed bar widths to align nicely
     BAR_FMT_DEFAULT_NESTED = (
         "{percentage:3.0f}%|{bar:10}|{desc:{ncols_desc}.{ncols_desc}}"
-        "{n_fmt}/{total_fmt}"
-        " [{elapsed}<{remaining}, {rate_fmt:>11}{postfix}]"
+        "{postfix[info]}{n_fmt}/{total_fmt}"
+        " [{elapsed}<{remaining}, {rate_fmt:>11}]"
     )
     BAR_FMT_NOTOTAL = (
-        "{desc:{ncols_desc}.{ncols_desc}}{n_fmt}"
-        " [{elapsed}, {rate_fmt:>11}{postfix}]"
+        "{desc}{bar:b}|{postfix[info]}{n_fmt} [{elapsed}, {rate_fmt:>11}]"
     )
     BYTES_DEFAULTS = dict(
         unit="B", unit_scale=True, unit_divisor=1024, miniters=1
@@ -47,6 +46,7 @@ class Tqdm(tqdm):
         bytes=False,  # pylint: disable=W0622
         file=None,
         total=None,
+        postfix=None,
         **kwargs
     ):
         """
@@ -68,7 +68,6 @@ class Tqdm(tqdm):
             kwargs.setdefault("unit_scale", total > 999 if total else True)
         if file is None:
             file = sys.stderr
-        self.desc_persist = desc
         # auto-disable based on `logger.level`
         if not disable:
             disable = logger.getEffectiveLevel() > level
@@ -89,6 +88,7 @@ class Tqdm(tqdm):
             total=total,
             **kwargs
         )
+        self.postfix = postfix or {"info": ""}
         if bar_format is None:
             if self.__len__():
                 self.bar_format = (
@@ -102,11 +102,11 @@ class Tqdm(tqdm):
             self.bar_format = bar_format
         self.refresh()
 
-    def update_desc(self, desc, n=1):
+    def update_msg(self, msg, n=1):
         """
-        Calls `set_description_str(desc)` and `update(n)`
+        Sets `msg` as a postfix and calls `update(n)`.
         """
-        self.set_description_str(desc, refresh=False)
+        self.postfix["info"] = " %s |" % msg
         self.update(n)
 
     def update_to(self, current, total=None):
@@ -114,13 +114,27 @@ class Tqdm(tqdm):
             self.total = total  # pylint: disable=W0613,W0201
         self.update(current - self.n)
 
+    def wrap_fn(self, fn, callback=None):
+        """
+        Returns a wrapped `fn` which calls `callback()` on each call.
+        `callback` is `self.update` by default.
+        """
+        if callback is None:
+            callback = self.update
+
+        def wrapped(*args, **kwargs):
+            res = fn(*args, **kwargs)
+            callback()
+            return res
+
+        return wrapped
+
     def close(self):
-        if self.desc_persist is not None:
-            self.set_description_str(self.desc_persist, refresh=False)
-        # unknown/zero ETA
-        self.bar_format = self.bar_format.replace("<{remaining}", "")
-        # remove completed bar
-        self.bar_format = self.bar_format.replace("|{bar:10}|", " ")
+        self.postfix["info"] = ""
+        # remove ETA (either unknown or zero); remove completed bar
+        self.bar_format = self.bar_format.replace("<{remaining}", "").replace(
+            "|{bar:10}|", " "
+        )
         super().close()
 
     @property
@@ -128,12 +142,15 @@ class Tqdm(tqdm):
         """inject `ncols_desc` to fill the display width (`ncols`)"""
         d = super().format_dict
         ncols = d["ncols"] or 80
-        ncols_desc = ncols - len(self.format_meter(ncols_desc=1, **d)) + 1
-        ncols_desc = max(ncols_desc, 0)
-        if ncols_desc:
-            d["ncols_desc"] = ncols_desc
+        # assumes `bar_format` has max one of ("ncols_desc" & "ncols_info")
+        ncols_left = (
+            ncols - len(self.format_meter(ncols_desc=1, ncols_info=1, **d)) + 1
+        )
+        ncols_left = max(ncols_left, 0)
+        if ncols_left:
+            d["ncols_desc"] = d["ncols_info"] = ncols_left
         else:
             # work-around for zero-width description
-            d["ncols_desc"] = 1
+            d["ncols_desc"] = d["ncols_info"] = 1
             d["prefix"] = ""
         return d

dvc/prompt.py

@@ -38,7 +38,7 @@ def confirm(statement):
     Returns:
         bool: whether or not specified statement was confirmed.
     """
-    prompt = "{statement} [y/n]".format(statement=statement)
+    prompt = f"{statement} [y/n]"
     answer = _ask(prompt, limited_to=["yes", "no", "y", "n"])
     return answer and answer.startswith("y")
 
@@ -52,5 +52,5 @@ def password(statement):
     Returns:
         str: password entered by the user.
     """
-    logger.info("{statement}: ".format(statement=statement))
+    logger.info(f"{statement}: ")
     return getpass("")

dvc/remote/__init__.py

@@ -1,47 +1,46 @@
 import posixpath
 from urllib.parse import urlparse
 
-from dvc.remote.azure import RemoteAZURE
-from dvc.remote.gdrive import RemoteGDrive
-from dvc.remote.gs import RemoteGS
-from dvc.remote.hdfs import RemoteHDFS
-from dvc.remote.http import RemoteHTTP
-from dvc.remote.https import RemoteHTTPS
-from dvc.remote.local import RemoteLOCAL
-from dvc.remote.oss import RemoteOSS
-from dvc.remote.s3 import RemoteS3
-from dvc.remote.ssh import RemoteSSH
+from dvc.remote.azure import AzureRemoteTree
+from dvc.remote.base import Remote
+from dvc.remote.gdrive import GDriveRemoteTree
+from dvc.remote.gs import GSRemoteTree
+from dvc.remote.hdfs import HDFSRemoteTree
+from dvc.remote.http import HTTPRemoteTree
+from dvc.remote.https import HTTPSRemoteTree
+from dvc.remote.local import LocalRemote, LocalRemoteTree
+from dvc.remote.oss import OSSRemoteTree
+from dvc.remote.s3 import S3RemoteTree
+from dvc.remote.ssh import SSHRemote, SSHRemoteTree
 
-
-REMOTES = [
-    RemoteAZURE,
-    RemoteGDrive,
-    RemoteGS,
-    RemoteHDFS,
-    RemoteHTTP,
-    RemoteHTTPS,
-    RemoteS3,
-    RemoteSSH,
-    RemoteOSS,
-    # NOTE: RemoteLOCAL is the default
+TREES = [
+    AzureRemoteTree,
+    GDriveRemoteTree,
+    GSRemoteTree,
+    HDFSRemoteTree,
+    HTTPRemoteTree,
+    HTTPSRemoteTree,
+    S3RemoteTree,
+    SSHRemoteTree,
+    OSSRemoteTree,
+    # NOTE: LocalRemoteTree is the default
 ]
 
 
-def _get(remote_conf):
-    for remote in REMOTES:
-        if remote.supported(remote_conf):
-            return remote
-    return RemoteLOCAL
+def _get_tree(remote_conf):
+    for tree_cls in TREES:
+        if tree_cls.supported(remote_conf):
+            return tree_cls
+    return LocalRemoteTree
 
 
-def Remote(repo, **kwargs):
+def _get_conf(repo, **kwargs):
     name = kwargs.get("name")
     if name:
         remote_conf = repo.config["remote"][name.lower()]
     else:
         remote_conf = kwargs
-    remote_conf = _resolve_remote_refs(repo.config, remote_conf)
-    return _get(remote_conf)(repo, remote_conf)
+    return _resolve_remote_refs(repo.config, remote_conf)
 
 
 def _resolve_remote_refs(config, remote_conf):
@@ -73,3 +72,17 @@ def _resolve_remote_refs(config, remote_conf):
     base = config["remote"][parsed.netloc]
     url = posixpath.join(base["url"], parsed.path.lstrip("/"))
     return {**base, **remote_conf, "url": url}
+
+
+def get_cloud_tree(repo, **kwargs):
+    remote_conf = _get_conf(repo, **kwargs)
+    return _get_tree(remote_conf)(repo, remote_conf)
+
+
+def get_remote(repo, **kwargs):
+    tree = get_cloud_tree(repo, **kwargs)
+    if tree.scheme == "local":
+        return LocalRemote(tree)
+    if tree.scheme == "ssh":
+        return SSHRemote(tree)
+    return Remote(tree)

dvc/remote/azure.py

@@ -1,77 +1,73 @@
 import logging
 import os
-import re
-from datetime import datetime, timedelta
-from urllib.parse import urlparse
 import threading
+from datetime import datetime, timedelta
 
 from funcy import cached_property, wrap_prop
 
 from dvc.path_info import CloudURLInfo
 from dvc.progress import Tqdm
-from dvc.remote.base import RemoteBASE
+from dvc.remote.base import BaseRemoteTree
 from dvc.scheme import Schemes
 
-
 logger = logging.getLogger(__name__)
 
 
-class RemoteAZURE(RemoteBASE):
+class AzureRemoteTree(BaseRemoteTree):
     scheme = Schemes.AZURE
-    path_cls = CloudURLInfo
-    REGEX = (
-        r"azure://((?P<path>[^=;]*)?|("
-        # backward compatibility
-        r"(ContainerName=(?P<container_name>[^;]+);?)?"
-        r"(?P<connection_string>.+)?)?)$"
-    )
-    REQUIRES = {"azure-storage-blob": "azure.storage.blob"}
+    PATH_CLS = CloudURLInfo
+    REQUIRES = {
+        "azure-storage-blob": "azure.storage.blob",
+        "knack": "knack",
+    }
     PARAM_CHECKSUM = "etag"
     COPY_POLL_SECONDS = 5
+    LIST_OBJECT_PAGE_SIZE = 5000
 
     def __init__(self, repo, config):
         super().__init__(repo, config)
 
         url = config.get("url", "azure://")
+        self.path_info = self.PATH_CLS(url)
 
-        match = re.match(self.REGEX, url)  # backward compatibility
-        path = match.group("path")
-        bucket = (
-            urlparse(url if path else "").netloc
-            or match.group("container_name")  # backward compatibility
-            or os.getenv("AZURE_STORAGE_CONTAINER_NAME")
+        if not self.path_info.bucket:
+            container = self._az_config.get("storage", "container_name", None)
+            self.path_info = self.PATH_CLS(f"azure://{container}")
+
+        self._conn_kwargs = {
+            opt: config.get(opt) or self._az_config.get("storage", opt, None)
+            for opt in ["connection_string", "sas_token"]
+        }
+        self._conn_kwargs["account_name"] = self._az_config.get(
+            "storage", "account", None
+        )
+        self._conn_kwargs["account_key"] = self._az_config.get(
+            "storage", "key", None
         )
 
-        self.connection_string = (
-            config.get("connection_string")
-            or match.group("connection_string")  # backward compatibility
-            or os.getenv("AZURE_STORAGE_CONNECTION_STRING")
-        )
+    @cached_property
+    def _az_config(self):
+        # NOTE: ideally we would've used get_default_cli().config from
+        # azure.cli.core, but azure-cli-core has a lot of conflicts with other
+        # dependencies. So instead we are just use knack directly
+        from knack.config import CLIConfig
 
-        if not bucket:
-            raise ValueError("azure storage container name missing")
-
-        if not self.connection_string:
-            raise ValueError("azure storage connection string missing")
-
-        self.path_info = (
-            self.path_cls(url)
-            if path
-            else self.path_cls.from_parts(scheme=self.scheme, netloc=bucket)
+        config_dir = os.getenv(
+            "AZURE_CONFIG_DIR", os.path.expanduser(os.path.join("~", ".azure"))
         )
+        return CLIConfig(config_dir=config_dir, config_env_var_prefix="AZURE")
 
     @wrap_prop(threading.Lock())
     @cached_property
     def blob_service(self):
+        # pylint: disable=no-name-in-module
         from azure.storage.blob import BlockBlobService
         from azure.common import AzureMissingResourceHttpError
 
-        logger.debug("URL {}".format(self.path_info))
-        logger.debug("Connection string {}".format(self.connection_string))
-        blob_service = BlockBlobService(
-            connection_string=self.connection_string
-        )
-        logger.debug("Container name {}".format(self.path_info.bucket))
+        logger.debug(f"URL {self.path_info}")
+        logger.debug(f"Connection options {self._conn_kwargs}")
+        blob_service = BlockBlobService(**self._conn_kwargs)
+        logger.debug(f"Container name {self.path_info.bucket}")
         try:  # verify that container exists
             blob_service.list_blobs(
                 self.path_info.bucket, delimiter="/", num_results=1
@@ -80,12 +76,33 @@ class RemoteAZURE(RemoteBASE):
             blob_service.create_container(self.path_info.bucket)
         return blob_service
 
-    def remove(self, path_info):
-        if path_info.scheme != self.scheme:
-            raise NotImplementedError
+    def get_etag(self, path_info):
+        etag = self.blob_service.get_blob_properties(
+            path_info.bucket, path_info.path
+        ).properties.etag
+        return etag.strip('"')
 
-        logger.debug("Removing {}".format(path_info))
-        self.blob_service.delete_blob(path_info.bucket, path_info.path)
+    def _generate_download_url(self, path_info, expires=3600):
+        from azure.storage.blob import (  # pylint:disable=no-name-in-module
+            BlobPermissions,
+        )
+
+        expires_at = datetime.utcnow() + timedelta(seconds=expires)
+
+        sas_token = self.blob_service.generate_blob_shared_access_signature(
+            path_info.bucket,
+            path_info.path,
+            permission=BlobPermissions.READ,
+            expiry=expires_at,
+        )
+        download_url = self.blob_service.make_blob_url(
+            path_info.bucket, path_info.path, sas_token=sas_token
+        )
+        return download_url
+
+    def exists(self, path_info):
+        paths = self._list_paths(path_info.bucket, path_info.path)
+        return any(path_info.path == path for path in paths)
 
     def _list_paths(self, bucket, prefix):
         blob_service = self.blob_service
@@ -103,8 +120,26 @@ class RemoteAZURE(RemoteBASE):
 
             next_marker = blobs.next_marker
 
-    def list_cache_paths(self):
-        return self._list_paths(self.path_info.bucket, self.path_info.path)
+    def walk_files(self, path_info, **kwargs):
+        if not kwargs.pop("prefix", False):
+            path_info = path_info / ""
+        for fname in self._list_paths(
+            path_info.bucket, path_info.path, **kwargs
+        ):
+            if fname.endswith("/"):
+                continue
+
+            yield path_info.replace(path=fname)
+
+    def remove(self, path_info):
+        if path_info.scheme != self.scheme:
+            raise NotImplementedError
+
+        logger.debug(f"Removing {path_info}")
+        self.blob_service.delete_blob(path_info.bucket, path_info.path)
+
+    def get_file_hash(self, path_info):
+        return self.get_etag(path_info)
 
     def _upload(
         self, from_file, to_info, name=None, no_progress_bar=False, **_kwargs
@@ -127,23 +162,3 @@ class RemoteAZURE(RemoteBASE):
                 to_file,
                 progress_callback=pbar.update_to,
             )
-
-    def exists(self, path_info):
-        paths = self._list_paths(path_info.bucket, path_info.path)
-        return any(path_info.path == path for path in paths)
-
-    def _generate_download_url(self, path_info, expires=3600):
-        from azure.storage.blob import BlobPermissions
-
-        expires_at = datetime.utcnow() + timedelta(seconds=expires)
-
-        sas_token = self.blob_service.generate_blob_shared_access_signature(
-            path_info.bucket,
-            path_info.path,
-            permission=BlobPermissions.READ,
-            expiry=expires_at,
-        )
-        download_url = self.blob_service.make_blob_url(
-            path_info.bucket, path_info.path, sas_token=sas_token
-        )
-        return download_url

dvc/remote/gdrive.py

@@ -1,70 +1,72 @@
+import io
+import logging
 import os
 import posixpath
-import logging
 import re
 import threading
+from collections import defaultdict
+from contextlib import contextmanager
 from urllib.parse import urlparse
 
-from funcy import retry, compose, decorator, wrap_with
+from funcy import cached_property, retry, wrap_prop, wrap_with
 from funcy.py3 import cat
 
-from dvc.progress import Tqdm
-from dvc.scheme import Schemes
+from dvc.exceptions import DvcException, FileMissingError
 from dvc.path_info import CloudURLInfo
-from dvc.remote.base import RemoteBASE
-from dvc.exceptions import DvcException
-from dvc.utils import tmp_fname, format_link
+from dvc.progress import Tqdm
+from dvc.remote.base import BaseRemoteTree
+from dvc.scheme import Schemes
+from dvc.utils import format_link, tmp_fname
+from dvc.utils.stream import IterStream
 
 logger = logging.getLogger(__name__)
 FOLDER_MIME_TYPE = "application/vnd.google-apps.folder"
 
 
-class GDriveRetriableError(DvcException):
-    pass
+class GDriveAuthError(DvcException):
+    def __init__(self, cred_location):
+
+        if cred_location:
+            message = (
+                "GDrive remote auth failed with credentials in '{}'.\n"
+                "Backup first, remove or fix them, and run DVC again.\n"
+                "It should do auth again and refresh the credentials.\n\n"
+                "Details:".format(cred_location)
+            )
+        else:
+            message = "Failed to authenticate GDrive remote"
+
+        super().__init__(message)
 
 
-class GDrivePathNotFound(DvcException):
-    def __init__(self, path_info):
-        super().__init__("Google Drive path '{}' not found.".format(path_info))
+def _gdrive_retry(func):
+    def should_retry(exc):
+        from pydrive2.files import ApiRequestError
 
+        if not isinstance(exc, ApiRequestError):
+            return False
 
-class GDriveAccessTokenRefreshError(DvcException):
-    def __init__(self):
-        super().__init__("Google Drive access token refreshment is failed.")
+        error_code = exc.error.get("code", 0)
+        result = False
+        if 500 <= error_code < 600:
+            result = True
 
+        if error_code == 403:
+            result = exc.GetField("reason") in [
+                "userRateLimitExceeded",
+                "rateLimitExceeded",
+            ]
+        if result:
+            logger.debug(f"Retrying GDrive API call, error: {exc}.")
 
-class GDriveMissedCredentialKeyError(DvcException):
-    def __init__(self, path):
-        super().__init__(
-            "Google Drive user credentials file '{}' "
-            "misses value for key.".format(path)
-        )
+        return result
 
-
-@decorator
-def _wrap_pydrive_retriable(call):
-    from pydrive2.files import ApiRequestError
-
-    try:
-        result = call()
-    except ApiRequestError as exception:
-        retry_codes = ["403", "500", "502", "503", "504"]
-        if any(
-            "HttpError {}".format(code) in str(exception)
-            for code in retry_codes
-        ):
-            raise GDriveRetriableError("Google API request failed")
-        raise
-    return result
-
-
-gdrive_retry = compose(
-    # 15 tries, start at 0.5s, multiply by golden ratio, cap at 20s
-    retry(
-        15, GDriveRetriableError, timeout=lambda a: min(0.5 * 1.618 ** a, 20)
-    ),
-    _wrap_pydrive_retriable,
-)
+    # 16 tries, start at 0.5s, multiply by golden ratio, cap at 20s
+    return retry(
+        16,
+        timeout=lambda a: min(0.5 * 1.618 ** a, 20),
+        filter_errors=should_retry,
+    )(func)
 
 
 class GDriveURLInfo(CloudURLInfo):
@@ -82,175 +84,277 @@ class GDriveURLInfo(CloudURLInfo):
         self._spath = re.sub("/{2,}", "/", self._spath.rstrip("/"))
 
 
-class RemoteGDrive(RemoteBASE):
+class GDriveRemoteTree(BaseRemoteTree):
     scheme = Schemes.GDRIVE
-    path_cls = GDriveURLInfo
+    PATH_CLS = GDriveURLInfo
     REQUIRES = {"pydrive2": "pydrive2"}
-    DEFAULT_NO_TRAVERSE = False
     DEFAULT_VERIFY = True
+    # Always prefer traverse for GDrive since API usage quotas are a concern.
+    TRAVERSE_WEIGHT_MULTIPLIER = 1
+    TRAVERSE_PREFIX_LEN = 2
 
-    GDRIVE_USER_CREDENTIALS_DATA = "GDRIVE_USER_CREDENTIALS_DATA"
+    GDRIVE_CREDENTIALS_DATA = "GDRIVE_CREDENTIALS_DATA"
     DEFAULT_USER_CREDENTIALS_FILE = "gdrive-user-credentials.json"
 
+    DEFAULT_GDRIVE_CLIENT_ID = "710796635688-iivsgbgsb6uv1fap6635dhvuei09o66c.apps.googleusercontent.com"  # noqa: E501
+    DEFAULT_GDRIVE_CLIENT_SECRET = "a1Fz59uTpVNeG_VGuSKDLJXv"
+
     def __init__(self, repo, config):
         super().__init__(repo, config)
-        self.path_info = self.path_cls(config["url"])
+
+        self.path_info = self.PATH_CLS(config["url"])
 
         if not self.path_info.bucket:
             raise DvcException(
-                "Empty Google Drive URL '{}'. Learn more at "
-                "{}.".format(
+                "Empty GDrive URL '{}'. Learn more at {}".format(
                     config["url"],
                     format_link("https://man.dvc.org/remote/add"),
                 )
             )
 
         self._bucket = self.path_info.bucket
+        self._trash_only = config.get("gdrive_trash_only")
+        self._use_service_account = config.get("gdrive_use_service_account")
+        self._service_account_email = config.get(
+            "gdrive_service_account_email"
+        )
+        self._service_account_user_email = config.get(
+            "gdrive_service_account_user_email"
+        )
+        self._service_account_p12_file_path = config.get(
+            "gdrive_service_account_p12_file_path"
+        )
         self._client_id = config.get("gdrive_client_id")
         self._client_secret = config.get("gdrive_client_secret")
-        if not self._client_id or not self._client_secret:
-            raise DvcException(
-                "Please specify Google Drive's client id and "
-                "secret in DVC config. Learn more at "
-                "{}.".format(format_link("https://man.dvc.org/remote/add"))
-            )
+        self._validate_config()
         self._gdrive_user_credentials_path = (
             tmp_fname(os.path.join(self.repo.tmp_dir, ""))
-            if os.getenv(RemoteGDrive.GDRIVE_USER_CREDENTIALS_DATA)
+            if os.getenv(GDriveRemoteTree.GDRIVE_CREDENTIALS_DATA)
             else config.get(
                 "gdrive_user_credentials_file",
                 os.path.join(
-                    self.repo.tmp_dir, self.DEFAULT_USER_CREDENTIALS_FILE
+                    self.repo.tmp_dir, self.DEFAULT_USER_CREDENTIALS_FILE,
                 ),
             )
         )
 
-        self._list_params = None
-        self._gdrive = None
+    def _validate_config(self):
+        # Validate Service Account configuration
+        if self._use_service_account and (
+            not self._service_account_email
+            or not self._service_account_p12_file_path
+        ):
+            raise DvcException(
+                "To use service account, set `gdrive_service_account_email`,\n"
+                "`gdrive_service_account_p12_file_path`, and optionally "
+                "`gdrive_service_account_user_email`\nin DVC config. "
+                "Learn more at {}".format(
+                    format_link("https://man.dvc.org/remote/modify")
+                )
+            )
 
-        self._cache_initialized = False
-        self._remote_root_id = None
-        self._cached_dirs = None
-        self._cached_ids = None
-
-    @property
-    @wrap_with(threading.RLock())
-    def drive(self):
-        from pydrive2.auth import RefreshError
-
-        if not self._gdrive:
-            from pydrive2.auth import GoogleAuth
-            from pydrive2.drive import GoogleDrive
-
-            if os.getenv(RemoteGDrive.GDRIVE_USER_CREDENTIALS_DATA):
-                with open(
-                    self._gdrive_user_credentials_path, "w"
-                ) as credentials_file:
-                    credentials_file.write(
-                        os.getenv(RemoteGDrive.GDRIVE_USER_CREDENTIALS_DATA)
+        # Validate OAuth 2.0 Client ID configuration
+        if not self._use_service_account:
+            if bool(self._client_id) != bool(self._client_secret):
+                raise DvcException(
+                    "Please specify GDrive's client ID and secret in "
+                    "DVC config or omit both to use the defaults.\n"
+                    "Learn more at {}".format(
+                        format_link("https://man.dvc.org/remote/modify")
                     )
+                )
 
-            GoogleAuth.DEFAULT_SETTINGS["client_config_backend"] = "settings"
-            GoogleAuth.DEFAULT_SETTINGS["client_config"] = {
-                "client_id": self._client_id,
-                "client_secret": self._client_secret,
+    @cached_property
+    def credentials_location(self):
+        """
+        Helper to determine where will GDrive remote read credentials from.
+        Useful for tests, exception messages, etc. Returns either env variable
+        name if it's set or actual path to the credentials file.
+        """
+        if os.getenv(GDriveRemoteTree.GDRIVE_CREDENTIALS_DATA):
+            return GDriveRemoteTree.GDRIVE_CREDENTIALS_DATA
+        if os.path.exists(self._gdrive_user_credentials_path):
+            return self._gdrive_user_credentials_path
+        return None
+
+    @staticmethod
+    def _validate_credentials(auth, settings):
+        """
+        Detects discrepancy in DVC config and cached credentials file.
+        Usually happens when a second remote is added and it is using
+        the same credentials default file. Or when someones decides to change
+        DVC config client id or secret but forgets to remove the cached
+        credentials file.
+        """
+        if not os.getenv(GDriveRemoteTree.GDRIVE_CREDENTIALS_DATA):
+            if (
+                settings["client_config"]["client_id"]
+                != auth.credentials.client_id
+                or settings["client_config"]["client_secret"]
+                != auth.credentials.client_secret
+            ):
+                logger.warning(
+                    "Client ID and secret configured do not match the "
+                    "actual ones used\nto access the remote. Do you "
+                    "use multiple GDrive remotes and forgot to\nset "
+                    "`gdrive_user_credentials_file` for one or more of them? "
+                    "Learn more at\n{}.\n".format(
+                        format_link("https://man.dvc.org/remote/modify")
+                    )
+                )
+
+    @wrap_prop(threading.RLock())
+    @cached_property
+    def _drive(self):
+        from pydrive2.auth import GoogleAuth
+        from pydrive2.drive import GoogleDrive
+
+        if os.getenv(GDriveRemoteTree.GDRIVE_CREDENTIALS_DATA):
+            with open(self._gdrive_user_credentials_path, "w") as cred_file:
+                cred_file.write(
+                    os.getenv(GDriveRemoteTree.GDRIVE_CREDENTIALS_DATA)
+                )
+
+        auth_settings = {
+            "client_config_backend": "settings",
+            "save_credentials": True,
+            "save_credentials_backend": "file",
+            "save_credentials_file": self._gdrive_user_credentials_path,
+            "get_refresh_token": True,
+            "oauth_scope": [
+                "https://www.googleapis.com/auth/drive",
+                "https://www.googleapis.com/auth/drive.appdata",
+            ],
+        }
+
+        if self._use_service_account:
+            auth_settings["service_config"] = {
+                "client_service_email": self._service_account_email,
+                "client_user_email": self._service_account_user_email,
+                "client_pkcs12_file_path": self._service_account_p12_file_path,
+            }
+        else:
+            auth_settings["client_config"] = {
+                "client_id": self._client_id or self.DEFAULT_GDRIVE_CLIENT_ID,
+                "client_secret": self._client_secret
+                or self.DEFAULT_GDRIVE_CLIENT_SECRET,
                 "auth_uri": "https://accounts.google.com/o/oauth2/auth",
                 "token_uri": "https://oauth2.googleapis.com/token",
                 "revoke_uri": "https://oauth2.googleapis.com/revoke",
                 "redirect_uri": "",
             }
-            GoogleAuth.DEFAULT_SETTINGS["save_credentials"] = True
-            GoogleAuth.DEFAULT_SETTINGS["save_credentials_backend"] = "file"
-            GoogleAuth.DEFAULT_SETTINGS[
-                "save_credentials_file"
-            ] = self._gdrive_user_credentials_path
-            GoogleAuth.DEFAULT_SETTINGS["get_refresh_token"] = True
-            GoogleAuth.DEFAULT_SETTINGS["oauth_scope"] = [
-                "https://www.googleapis.com/auth/drive",
-                "https://www.googleapis.com/auth/drive.appdata",
-            ]
 
-            # Pass non existent settings path to force DEFAULT_SETTINGS loading
-            gauth = GoogleAuth(settings_file="")
+        GoogleAuth.DEFAULT_SETTINGS.update(auth_settings)
 
-            try:
+        # Pass non existent settings path to force DEFAULT_SETTINGS loadings
+        gauth = GoogleAuth(settings_file="")
+
+        try:
+            logger.debug(
+                "GDrive remote auth with config '{}'.".format(
+                    GoogleAuth.DEFAULT_SETTINGS
+                )
+            )
+            if self._use_service_account:
+                gauth.ServiceAuth()
+            else:
                 gauth.CommandLineAuth()
-            except RefreshError as exc:
-                raise GDriveAccessTokenRefreshError from exc
-            except KeyError as exc:
-                raise GDriveMissedCredentialKeyError(
-                    self._gdrive_user_credentials_path
-                ) from exc
-            # Handle pydrive2.auth.AuthenticationError and other auth failures
-            except Exception as exc:
-                raise DvcException(
-                    "Google Drive authentication failed"
-                ) from exc
-            finally:
-                if os.getenv(RemoteGDrive.GDRIVE_USER_CREDENTIALS_DATA):
-                    os.remove(self._gdrive_user_credentials_path)
+                GDriveRemoteTree._validate_credentials(gauth, auth_settings)
 
-            self._gdrive = GoogleDrive(gauth)
+        # Handle AuthenticationError, RefreshError and other auth failures
+        # It's hard to come up with a narrow exception, since PyDrive throws
+        # a lot of different errors - broken credentials file, refresh token
+        # expired, flow failed, etc.
+        except Exception as exc:
+            raise GDriveAuthError(self.credentials_location) from exc
+        finally:
+            if os.getenv(GDriveRemoteTree.GDRIVE_CREDENTIALS_DATA):
+                os.remove(self._gdrive_user_credentials_path)
 
-        return self._gdrive
+        return GoogleDrive(gauth)
 
-    @wrap_with(threading.RLock())
-    def _initialize_cache(self):
-        if self._cache_initialized:
-            return
+    @wrap_prop(threading.RLock())
+    @cached_property
+    def _ids_cache(self):
+        cache = {
+            "dirs": defaultdict(list),
+            "ids": {},
+            "root_id": self._get_item_id(
+                self.path_info,
+                use_cache=False,
+                hint="Confirm the directory exists and you can access it.",
+            ),
+        }
 
-        cached_dirs = {}
-        cached_ids = {}
-        self._remote_root_id = self._get_remote_id(self.path_info)
-        for dir1 in self.gdrive_list_item(
-            "'{}' in parents and trashed=false".format(self._remote_root_id)
+        self._cache_path_id(self.path_info.path, cache["root_id"], cache)
+
+        for item in self._gdrive_list(
+            "'{}' in parents and trashed=false".format(cache["root_id"])
         ):
-            remote_path = posixpath.join(self.path_info.path, dir1["title"])
-            cached_dirs.setdefault(remote_path, []).append(dir1["id"])
-            cached_ids[dir1["id"]] = dir1["title"]
+            item_path = (self.path_info / item["title"]).path
+            self._cache_path_id(item_path, item["id"], cache)
 
-        self._cached_dirs = cached_dirs
-        self._cached_ids = cached_ids
-        self._cache_initialized = True
+        return cache
 
-    @property
-    def cached_dirs(self):
-        if not self._cache_initialized:
-            self._initialize_cache()
-        return self._cached_dirs
+    def _cache_path_id(self, path, item_id, cache=None):
+        cache = cache or self._ids_cache
+        cache["dirs"][path].append(item_id)
+        cache["ids"][item_id] = path
 
-    @property
-    def cached_ids(self):
-        if not self._cache_initialized:
-            self._initialize_cache()
-        return self._cached_ids
-
-    @property
-    def remote_root_id(self):
-        if not self._cache_initialized:
-            self._initialize_cache()
-        return self._remote_root_id
-
-    @property
-    def list_params(self):
-        if not self._list_params:
-            params = {"corpora": "default"}
-            if self._bucket != "root" and self._bucket != "appDataFolder":
-                params["driveId"] = self._get_remote_drive_id(self._bucket)
+    @cached_property
+    def _list_params(self):
+        params = {"corpora": "default"}
+        if self._bucket != "root" and self._bucket != "appDataFolder":
+            drive_id = self._gdrive_shared_drive_id(self._bucket)
+            if drive_id:
+                logger.debug(
+                    "GDrive remote '{}' is using shared drive id '{}'.".format(
+                        self.path_info, drive_id
+                    )
+                )
+                params["driveId"] = drive_id
                 params["corpora"] = "drive"
-            self._list_params = params
-        return self._list_params
+        return params
 
-    @gdrive_retry
-    def gdrive_upload_file(
+    @_gdrive_retry
+    def _gdrive_shared_drive_id(self, item_id):
+        from pydrive2.files import ApiRequestError
+
+        param = {"id": item_id}
+        # it does not create a file on the remote
+        item = self._drive.CreateFile(param)
+        # ID of the shared drive the item resides in.
+        # Only populated for items in shared drives.
+        try:
+            item.FetchMetadata("driveId")
+        except ApiRequestError as exc:
+            error_code = exc.error.get("code", 0)
+            if error_code == 404:
+                raise DvcException(
+                    "'{}' for '{}':\n\n"
+                    "1. Confirm the directory exists and you can access it.\n"
+                    "2. Make sure that credentials in '{}'\n"
+                    "   are correct for this remote e.g. "
+                    "use the `gdrive_user_credentials_file` config\n"
+                    "   option if you use multiple GDrive remotes with "
+                    "different email accounts.\n\nDetails".format(
+                        item_id, self.path_info, self.credentials_location
+                    )
+                ) from exc
+            raise
+
+        return item.get("driveId", None)
+
+    @_gdrive_retry
+    def _gdrive_upload_file(
         self,
         parent_id,
         title,
-        no_progress_bar=True,
+        no_progress_bar=False,
         from_file="",
         progress_name="",
     ):
-        item = self.drive.CreateFile(
+        item = self._drive.CreateFile(
             {"title": title, "parents": [{"id": parent_id}]}
         )
 
@@ -270,172 +374,209 @@ class RemoteGDrive(RemoteBASE):
                 item.Upload()
         return item
 
-    @gdrive_retry
-    def gdrive_download_file(
-        self, file_id, to_file, progress_name, no_progress_bar
+    @_gdrive_retry
+    def _gdrive_download_file(
+        self, item_id, to_file, progress_desc, no_progress_bar
     ):
-        param = {"id": file_id}
+        param = {"id": item_id}
         # it does not create a file on the remote
-        gdrive_file = self.drive.CreateFile(param)
-        bar_format = (
-            "Downloading {desc:{ncols_desc}.{ncols_desc}}... "
-            + Tqdm.format_sizeof(int(gdrive_file["fileSize"]), "B", 1024)
-        )
+        gdrive_file = self._drive.CreateFile(param)
+
         with Tqdm(
-            bar_format=bar_format, desc=progress_name, disable=no_progress_bar
-        ):
-            gdrive_file.GetContentFile(to_file)
+            desc=progress_desc,
+            disable=no_progress_bar,
+            bytes=True,
+            # explicit `bar_format` as `total` will be set by `update_to`
+            bar_format=Tqdm.BAR_FMT_DEFAULT,
+        ) as pbar:
+            gdrive_file.GetContentFile(to_file, callback=pbar.update_to)
 
-    def gdrive_list_item(self, query):
+    @contextmanager
+    @_gdrive_retry
+    def open(self, path_info, mode="r", encoding=None):
+        assert mode in {"r", "rt", "rb"}
+
+        item_id = self._get_item_id(path_info)
+        param = {"id": item_id}
+        # it does not create a file on the remote
+        gdrive_file = self._drive.CreateFile(param)
+        fd = gdrive_file.GetContentIOBuffer()
+        stream = IterStream(iter(fd))
+
+        if mode != "rb":
+            stream = io.TextIOWrapper(stream, encoding=encoding)
+
+        yield stream
+
+    @_gdrive_retry
+    def gdrive_delete_file(self, item_id):
+        from pydrive2.files import ApiRequestError
+
+        param = {"id": item_id}
+        # it does not create a file on the remote
+        item = self._drive.CreateFile(param)
+
+        try:
+            item.Trash() if self._trash_only else item.Delete()
+        except ApiRequestError as exc:
+            http_error_code = exc.error.get("code", 0)
+            if (
+                http_error_code == 403
+                and self._list_params["corpora"] == "drive"
+                and exc.GetField("location") == "file.permissions"
+            ):
+                raise DvcException(
+                    "Insufficient permissions to {}. You should have {} "
+                    "access level for the used shared drive. More details "
+                    "at {}.".format(
+                        "move the file into Trash"
+                        if self._trash_only
+                        else "permanently delete the file",
+                        "Manager or Content Manager"
+                        if self._trash_only
+                        else "Manager",
+                        "https://support.google.com/a/answer/7337554",
+                    )
+                ) from exc
+            raise
+
+    def _gdrive_list(self, query):
         param = {"q": query, "maxResults": 1000}
-        param.update(self.list_params)
+        param.update(self._list_params)
+        file_list = self._drive.ListFile(param)
 
-        file_list = self.drive.ListFile(param)
+        # Isolate and decorate fetching of remote drive items in pages.
+        get_list = _gdrive_retry(lambda: next(file_list, None))
 
-        # Isolate and decorate fetching of remote drive items in pages
-        get_list = gdrive_retry(lambda: next(file_list, None))
-
-        # Fetch pages until None is received, lazily flatten the thing
+        # Fetch pages until None is received, lazily flatten the thing.
         return cat(iter(get_list, None))
 
-    @wrap_with(threading.RLock())
-    def gdrive_create_dir(self, parent_id, title, remote_path):
-        if parent_id == self.remote_root_id:
-            cached = self.cached_dirs.get(remote_path, [])
-            if cached:
-                return cached[0]
-
-        item = self._create_remote_dir(parent_id, title)
-
-        if parent_id == self.remote_root_id:
-            self.cached_dirs.setdefault(remote_path, []).append(item["id"])
-            self.cached_ids[item["id"]] = item["title"]
-
-        return item["id"]
-
-    @gdrive_retry
-    def _create_remote_dir(self, parent_id, title):
+    @_gdrive_retry
+    def _gdrive_create_dir(self, parent_id, title):
         parent = {"id": parent_id}
-        item = self.drive.CreateFile(
+        item = self._drive.CreateFile(
             {"title": title, "parents": [parent], "mimeType": FOLDER_MIME_TYPE}
         )
         item.Upload()
         return item
 
-    @gdrive_retry
-    def _delete_remote_file(self, remote_id):
-        param = {"id": remote_id}
-        # it does not create a file on the remote
-        item = self.drive.CreateFile(param)
-        item.Delete()
+    @wrap_with(threading.RLock())
+    def _create_dir(self, parent_id, title, remote_path):
+        cached = self._ids_cache["dirs"].get(remote_path)
+        if cached:
+            return cached[0]
 
-    @gdrive_retry
-    def _get_remote_item(self, name, parents_ids):
-        if not parents_ids:
+        item = self._gdrive_create_dir(parent_id, title)
+
+        if parent_id == self._ids_cache["root_id"]:
+            self._cache_path_id(remote_path, item["id"])
+
+        return item["id"]
+
+    def _get_remote_item_ids(self, parent_ids, title):
+        if not parent_ids:
             return None
-        query = "({})".format(
+        query = "trashed=false and ({})".format(
             " or ".join(
-                "'{}' in parents".format(parent_id)
-                for parent_id in parents_ids
+                f"'{parent_id}' in parents" for parent_id in parent_ids
             )
         )
+        query += " and title='{}'".format(title.replace("'", "\\'"))
 
-        query += " and trashed=false and title='{}'".format(name)
+        # GDrive list API is case insensitive, we need to compare
+        # all results and pick the ones with the right title
+        return [
+            item["id"]
+            for item in self._gdrive_list(query)
+            if item["title"] == title
+        ]
 
-        # Remote might contain items with duplicated path (titles).
-        # We thus limit number of items.
-        param = {"q": query, "maxResults": 1}
-        param.update(self.list_params)
-
-        # Limit found remote items count to 1 in response
-        item_list = self.drive.ListFile(param).GetList()
-        return next(iter(item_list), None)
-
-    @gdrive_retry
-    def _get_remote_drive_id(self, remote_id):
-        param = {"id": remote_id}
-        # it does not create a file on the remote
-        item = self.drive.CreateFile(param)
-        item.FetchMetadata("driveId")
-        return item.get("driveId", None)
-
-    def _get_cached_remote_ids(self, path):
+    def _get_cached_item_ids(self, path, use_cache):
         if not path:
             return [self._bucket]
-        if self._cache_initialized:
-            if path == self.path_info.path:
-                return [self.remote_root_id]
-            return self.cached_dirs.get(path, [])
+        if use_cache:
+            return self._ids_cache["dirs"].get(path, [])
         return []
 
-    def _path_to_remote_ids(self, path, create):
-        remote_ids = self._get_cached_remote_ids(path)
-        if remote_ids:
-            return remote_ids
+    def _path_to_item_ids(self, path, create, use_cache):
+        item_ids = self._get_cached_item_ids(path, use_cache)
+        if item_ids:
+            return item_ids
 
-        parent_path, part = posixpath.split(path)
-        parent_ids = self._path_to_remote_ids(parent_path, create)
-        item = self._get_remote_item(part, parent_ids)
+        parent_path, title = posixpath.split(path)
+        parent_ids = self._path_to_item_ids(parent_path, create, use_cache)
+        item_ids = self._get_remote_item_ids(parent_ids, title)
+        if item_ids:
+            return item_ids
 
-        if not item:
-            return (
-                [self.gdrive_create_dir(parent_ids[0], part, path)]
-                if create
-                else []
-            )
+        return (
+            [self._create_dir(min(parent_ids), title, path)] if create else []
+        )
 
-        return [item["id"]]
-
-    def _get_remote_id(self, path_info, create=False):
+    def _get_item_id(self, path_info, create=False, use_cache=True, hint=None):
         assert path_info.bucket == self._bucket
 
-        remote_ids = self._path_to_remote_ids(path_info.path, create)
-        if not remote_ids:
-            raise GDrivePathNotFound(path_info)
+        item_ids = self._path_to_item_ids(path_info.path, create, use_cache)
+        if item_ids:
+            return min(item_ids)
 
-        return remote_ids[0]
+        assert not create
+        raise FileMissingError(path_info, hint)
 
     def exists(self, path_info):
         try:
-            self._get_remote_id(path_info)
-        except GDrivePathNotFound:
+            self._get_item_id(path_info)
+        except FileMissingError:
             return False
         else:
             return True
 
-    def _upload(self, from_file, to_info, name, no_progress_bar):
+    def _list_paths(self, prefix=None):
+        if not self._ids_cache["ids"]:
+            return
+
+        if prefix:
+            dir_ids = self._ids_cache["dirs"].get(prefix[:2])
+            if not dir_ids:
+                return
+        else:
+            dir_ids = self._ids_cache["ids"]
+        parents_query = " or ".join(
+            f"'{dir_id}' in parents" for dir_id in dir_ids
+        )
+        query = f"({parents_query}) and trashed=false"
+
+        for item in self._gdrive_list(query):
+            parent_id = item["parents"][0]["id"]
+            yield posixpath.join(
+                self._ids_cache["ids"][parent_id], item["title"]
+            )
+
+    def walk_files(self, path_info, **kwargs):
+        use_prefix = kwargs.pop("prefix", False)
+        if path_info == self.path_info or not use_prefix:
+            prefix = None
+        else:
+            prefix = path_info.path
+        for fname in self._list_paths(prefix=prefix, **kwargs):
+            yield path_info.replace(fname)
+
+    def remove(self, path_info):
+        item_id = self._get_item_id(path_info)
+        self.gdrive_delete_file(item_id)
+
+    def get_file_hash(self, path_info):
+        raise NotImplementedError
+
+    def _upload(self, from_file, to_info, name=None, no_progress_bar=False):
         dirname = to_info.parent
         assert dirname
-        parent_id = self._get_remote_id(dirname, True)
+        parent_id = self._get_item_id(dirname, True)
 
-        self.gdrive_upload_file(
+        self._gdrive_upload_file(
             parent_id, to_info.name, no_progress_bar, from_file, name
         )
 
-    def _download(self, from_info, to_file, name, no_progress_bar):
-        file_id = self._get_remote_id(from_info)
-        self.gdrive_download_file(file_id, to_file, name, no_progress_bar)
-
-    def all(self):
-        if not self.cached_ids:
-            return
-
-        query = "({})".format(
-            " or ".join(
-                "'{}' in parents".format(dir_id) for dir_id in self.cached_ids
-            )
-        )
-
-        query += " and trashed=false"
-        for file1 in self.gdrive_list_item(query):
-            parent_id = file1["parents"][0]["id"]
-            path = posixpath.join(self.cached_ids[parent_id], file1["title"])
-            try:
-                yield self.path_to_checksum(path)
-            except ValueError:
-                # We ignore all the non-cache looking files
-                logger.debug('Ignoring path as "non-cache looking"')
-
-    def remove(self, path_info):
-        remote_id = self._get_remote_id(path_info)
-        self._delete_remote_file(remote_id)
+    def _download(self, from_info, to_file, name=None, no_progress_bar=False):
+        item_id = self._get_item_id(from_info)
+        self._gdrive_download_file(item_id, to_file, name, no_progress_bar)