dvc: bump to 1.0.0a3

Fixed #3434

.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/PULL_REQUEST_TEMPLATE.md

@@ -1,8 +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. If the CLI API is changed, I have updated [tab completion scripts](https://github.com/iterative/dvc/tree/master/scripts/completion).
 
-* [ ] ❌ 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. 🙏
-

.gitignore

@@ -26,7 +26,7 @@ innosetup/config.ini
 .coverage
 .coverage.*
 
-*.swp
+*.sw?
 
 pip-wheel-metadata/
 .vscode/

.pre-commit-config.yaml

@@ -1,11 +1,44 @@
 repos:
--   repo: https://github.com/ambv/black
-    rev: 19.3b0
+- 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
-    rev: master
-    hooks:
-    - id: flake8
-      language_version: python3
+    -   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
+  repo: https://gitlab.com/pycqa/flake8
+  rev: 3.7.9
+- hooks:
+  - args:
+    - -i
+    - '2'
+    id: beautysh
+    language_version: python3
+  repo: https://github.com/lovesegfault/beautysh
+  rev: master
+- hooks:
+  - id: dvc-pre-commit
+    language_version: python3
+    stages:
+    - commit
+  - id: dvc-pre-push
+    language_version: python3
+    stages:
+    - push
+  - always_run: true
+    id: dvc-post-checkout
+    language_version: python3
+    stages:
+    - post-checkout
+  repo: https://github.com/iterative/dvc
+  rev: master

.pre-commit-hooks.yaml

@@ -0,0 +1,33 @@
+- args:
+  - git-hook
+  - pre-commit
+  entry: dvc
+  id: dvc-pre-commit
+  language: python
+  language_version: python3
+  name: DVC pre-commit
+  stages:
+  - commit
+  verbose: true
+- args:
+  - git-hook
+  - pre-push
+  entry: dvc
+  id: dvc-pre-push
+  language: python
+  language_version: python3
+  name: DVC pre-push
+  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
+  stages:
+  - post-checkout

.restyled.yaml

@@ -1,7 +1,7 @@
 ---
 restylers:
   - name: black
-    image: restyled/restyler-black:v19.3b0
+    image: restyled/restyler-black:v19.10b0
     command:
     - black
     arguments: []
@@ -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

@@ -13,8 +13,6 @@ stages:
   - check
   - test
   - build
-  - name: deploy
-    if: (branch = master OR tag is present) AND repo = iterative/dvc
 # Travis doesn't support testing python on Mac yet, so we need
 # to workaround it by installing it directly with brew.
 #
@@ -35,37 +33,31 @@ jobs:
     install:
     script: ./scripts/ci/check_patch.sh
   # test jobs
-  - name: "2.7 on Windows"
+  - name: "3.7 on Windows"
     stage: test
     os: windows           # Windows 10.0.17134 N/A Build 17134
     language: shell       # 'language: python' is an error on Travis CI Windows
     env:
-    - PY2=1
-  - name: "3.7 on Windows"
+      - PYTHON_VERSION=3.7.5
+      - PATH=/c/Python37:/c/Python37/Scripts:$PATH
+  - name: "3.8 on Windows"
     os: windows           # Windows 10.0.17134 N/A Build 17134
     language: shell       # 'language: python' is an error on Travis CI Windows
-  - name: "2.7 on Linux"
-    language: python
-    python: 2.7
     env:
-    - PY2=1
-  - name: "3.5 on Linux"
-    language: python
-    python: 3.5
+      - PYTHON_VERSION=3.8.0
+      - PATH=/c/Python38:/c/Python38/Scripts:$PATH
   - name: "3.6 on Linux"
     language: python
     python: 3.6
   - name: "3.7 on Linux"
     language: python
     python: 3.7
-  - name: "2.7 on Mac"
+  - name: "3.8 on Linux"
+    language: python
+    python: 3.8
+  - name: "3.7 on Mac"
     os: osx
-    osx_image: xcode9.4
-    env:
-    - PY2=1
-  - name: "3.6 on Mac"
-    os: osx
-    osx_image: xcode9.4
+    osx_image: xcode11.3
   # build jobs
   - name: "Mac pkg"
     stage: build
@@ -80,57 +72,42 @@ jobs:
     language: shell
     install:
     script: ./scripts/build_windows.cmd
+    env:
+      - PYTHON_VERSION=3.7.5
+      - PATH=/c/Python37:/c/Python37/Scripts:$PATH
   - name: "Linux pkgs"
     language: python
     python: 3.7
     before_install:
     install:
     script: ./scripts/build_posix.sh
-  - name: "Pypi pkgs"
+  - name: "PyPI pkgs"
     language: python
-    python: 3.7
+    python: 3.8
     script: ./scripts/build_package.sh
   - name: Snapcraft snap
+    language: python
+    python: 3.8
     addons:
      snaps:
      - name: snapcraft
        channel: stable
        confinement: classic
+     - name: review-tools
+       channel: stable
      - name: lxd
        channel: stable
     env:
     - SNAPCRAFT_IMAGE_INFO: '{"build_url": "$TRAVIS_BUILD_URL"}'
-    before_install:
+    install:
     - sudo /snap/bin/lxd.migrate -yes
     - sudo /snap/bin/lxd waitready
     - sudo /snap/bin/lxd init --auto
-    install:
+    - git fetch --tags
     script:
-    - sudo snapcraft --use-lxd
+    - ./scripts/build_snap.sh
     after_failure:
     - sudo journalctl -u snapd
-  # deploy jobs
-  - name: "Pypi pkgs"
-    if: tag is present
-    stage: deploy
-    language: python
-    python: 3.7
-    script: ./scripts/build_package.sh
-    deploy:
-    - provider: pypi
-      user:
-        secure: "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"
-      password:
-        secure: "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"
-      skip_existing: true
-      file_glob: true
-      file:
-        - dist/dvc*.whl
-        - dist/dvc*.tar.gz
-      skip_cleanup: true
-      on:
-        tags: true
-        repo: iterative/dvc
 
 before_install:
   - bash ./scripts/ci/before_install.sh
@@ -142,7 +119,6 @@ script:
   - bash ./scripts/ci/script.sh
 deploy:
   - provider: releases
-    condition: "[[ $(./scripts/ci/deploy_condition.sh) == 'true' ]]"
     api_key:
       secure: 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
     file_glob: true
@@ -151,9 +127,33 @@ deploy:
       - dvc*.deb
       - dvc*.pkg
       - dvc*.exe
-      - dvc*.snap
     skip_cleanup: true
     on:
+      condition: "$(./scripts/ci/deploy_condition.sh dvc*.rpm dvc*.deb dvc*.pkg dvc*.exe)"
       tags: true
       repo: iterative/dvc
       stage: build
+  - provider: pypi
+    user:
+      secure: "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"
+    password:
+      secure: "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"
+    skip_existing: true
+    file_glob: true
+    file:
+      - dist/dvc*.whl
+      - dist/dvc*.tar.gz
+    skip_cleanup: true
+    on:
+      condition: "$(./scripts/ci/deploy_condition.sh dist/dvc*.whl dist/dvc*.tar.gz)"
+      tags: true
+      repo: iterative/dvc
+      stage: build
+  - provider: script
+    skip_cleanup: true
+    script: "(echo $SNAP_TOKEN | snapcraft login --with -) && timeout 600 snapcraft push dvc_*.snap --release $SNAP_CHANNEL || echo timed out"
+    on:
+      all_branches: true
+      condition: "$(./scripts/ci/deploy_condition.sh dvc_*.snap) && ($TRAVIS_BRANCH = master || -n $TRAVIS_TAG)"
+      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>`_
@@ -10,29 +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://travis-ci.com/iterative/dvc.svg?branch=master
-  :target: https://travis-ci.com/iterative/dvc
-  :alt: Travis
+|Release| |CI| |Maintainability| |Coverage| |Donate| |DOI|
 
-.. 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
+|Snap| |Choco| |Brew| |Conda| |PyPI| |Packages|
 
 |
 
@@ -75,9 +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,
@@ -115,9 +91,52 @@ 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 ``--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
@@ -133,41 +152,11 @@ 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)
-----------------
-
-Download the latest ``dvc_*.snap`` from the
-GitHub `releases page <https://github.com/iterative/dvc/releases>`_.
-
-.. code-block:: bash
-
-   snap install dvc_*.snap --dangerous --classic
-
-Once ``dvc`` is released on the snap store
-(`pending request <https://forum.snapcraft.io/t/classic-confinement-request-for-dvc/14124>`_)
-there will be no need to download ``dvc_*.snap`` or use ``--dangerous``
-(``snap install dvc --classic`` would suffice).
-
 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>`_.
 
@@ -207,40 +196,43 @@ 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
 ============
@@ -254,3 +246,67 @@ 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

debian/changelog

@@ -2,4 +2,4 @@ dvc (0.75.b1) experimental; urgency=low
 
   * First native Debian package version.
 
- -- Dmitry Petrov <dmitry@dataversioncontrol.com>  Sat, 07 Dec 2019 09:49:28 +0300
+ -- Dmitry Petrov <dmitry@dvc.org>  Sat, 07 Dec 2019 09:49:28 +0300

debian/control

@@ -1,5 +1,5 @@
 Source: dvc
-Maintainer: Dmitry Petrov <dmitry@dataversioncontrol.com>
+Maintainer: Dmitry Petrov <dmitry@dvc.org>
 Section: python
 Priority: optional
 Build-Depends: dh-python, python3-setuptools, python3-all, debhelper (>= 9)

debian/copyright

@@ -1,10 +1,10 @@
 Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
 Upstream-Name: DVC
-Upstream-Contact: Dmitry Petrov <dmitry@dataversioncontrol.com>
+Upstream-Contact: Dmitry Petrov <dmitry@dvc.org>
 Source: https://github.com/iterative/dvc
 
 Files: *
-Copyright: Dmitry Petrov <dmitry@dataversioncontrol.com>
+Copyright: Dmitry Petrov <dmitry@dvc.org>
 License: Apache 2.0
  On Debian systems, the full text of the Apache 2.0
  License can be found in the file

dvc/__init__.py

@@ -3,19 +3,7 @@ DVC
 ----
 Make your data science projects reproducible and shareable.
 """
-from __future__ import unicode_literals
-
-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/__main__.py

@@ -1,6 +1,4 @@
-"""Main entry point for dvc command line tool."""
-from __future__ import unicode_literals
-
+"""Main entry point for DVC command line tool."""
 import sys
 
 from dvc.main import main

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
@@ -15,10 +15,10 @@ 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.utils import env2bool, is_binary, makedirs
-from dvc.utils.compat import str, FileNotFoundError
-
+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"):
@@ -54,17 +54,14 @@ def is_enabled():
         return False
 
     enabled = to_bool(
-        Config(validate=False)
-        .config.get(Config.SECTION_CORE, {})
-        .get(Config.SECTION_CORE_ANALYTICS, "true")
+        Config(validate=False).get("core", {}).get("analytics", "true")
     )
-
     logger.debug("Analytics is {}abled.".format("en" if enabled else "dis"))
 
     return enabled
 
 
-def send(report):
+def send(path):
     """
     Side effect: Removes the report after sending it.
 
@@ -75,16 +72,25 @@ def send(report):
     url = "https://analytics.dvc.org"
     headers = {"content-type": "application/json"}
 
-    with open(report, "rb") as fobj:
-        requests.post(url, data=fobj, headers=headers, timeout=5)
+    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
 
@@ -141,7 +147,7 @@ def _find_or_create_user_id():
 
     IDs are generated randomly with UUID.
     """
-    config_dir = Config.get_global_config_dir()
+    config_dir = Config.get_dir("global")
     fname = os.path.join(config_dir, "user_id")
     lockfile = os.path.join(config_dir, "user_id.lock")
 
@@ -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

@@ -1,27 +1,51 @@
 import os
+from contextlib import _GeneratorContextManager as GCM
 from contextlib import contextmanager
 
-try:
-    from contextlib import _GeneratorContextManager as GCM
-except ImportError:
-    from contextlib import GeneratorContextManager as GCM
-
-from dvc.utils.compat import urlparse
-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 the given URL is not a DVC repository."""
+
+    def __init__(self, url):
+        super().__init__(f"'{url}' is not a DVC repository.")
 
 
 def get_url(path, repo=None, rev=None, remote=None):
-    """Returns an url of a resource specified by path in repo"""
+    """
+    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:
-        abspath = os.path.join(_repo.root_dir, path)
-        out, = _repo.find_outs_by_path(abspath)
+        if not isinstance(_repo, Repo):
+            raise UrlNotDvcRepoError(_repo.url)
+        out = _repo.find_out_by_relpath(path)
         remote_obj = _repo.cloud.get_remote(remote)
         return str(remote_obj.checksum_to_path_info(out.checksum))
 
 
 def open(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
-    """Opens a specified resource as a file descriptor"""
+    """
+    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,
@@ -40,21 +64,24 @@ class _OpenContextManager(GCM):
 
     def __getattr__(self, name):
         raise AttributeError(
-            "dvc.api.open() should be used in a with statement"
+            "dvc.api.open() should be used in a with statement."
         )
 
 
 def _open(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
     with _make_repo(repo, rev=rev) as _repo:
-        abspath = os.path.join(_repo.root_dir, path)
-        with _repo.open(
-            abspath, remote=remote, mode=mode, encoding=encoding
+        with _repo.open_by_relpath(
+            path, remote=remote, mode=mode, encoding=encoding
         ) as fd:
             yield fd
 
 
 def read(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
-    """Read a specified resource into string"""
+    """
+    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:
@@ -62,10 +89,13 @@ def read(path, repo=None, rev=None, remote=None, mode="r", encoding=None):
 
 
 @contextmanager
-def _make_repo(repo_url, rev=None):
-    if not repo_url or urlparse(repo_url).scheme == "":
-        assert rev is None, "Custom revision is not supported for local repo"
-        yield Repo(repo_url)
-    else:
-        with external_repo(url=repo_url, rev=rev) as repo:
-            yield repo
+def _make_repo(repo_url=None, rev=None):
+    repo_url = repo_url or os.getcwd()
+    if rev is None and os.path.exists(repo_url):
+        try:
+            yield Repo(repo_url)
+            return
+        except NotDvcRepoError:
+            pass  # fallthrough to external_repo
+    with external_repo(url=repo_url, rev=rev) as repo:
+        yield repo

dvc/cache.py

@@ -1,28 +1,8 @@
-"""Manages cache of a dvc repo."""
-from __future__ import unicode_literals
-
-import os
+"""Manages cache of a DVC repo."""
 from collections import defaultdict
 
 from funcy import cached_property
 
-from dvc.config import Config
-from dvc.utils.compat import builtin_str
-
-
-class CacheConfig(object):
-    def __init__(self, config):
-        self.config = config
-
-    def set_dir(self, dname, level=None):
-        from dvc.remote.config import RemoteConfig
-
-        configobj = self.config.get_configobj(level)
-        path = RemoteConfig.resolve_path(dname, configobj.filename)
-        self.config.set(
-            Config.SECTION_CACHE, Config.SECTION_CACHE_DIR, path, level=level
-        )
-
 
 def _make_remote_property(name):
     """
@@ -56,12 +36,12 @@ def _make_remote_property(name):
 
         return Remote(self.repo, name=remote)
 
-    getter.__name__ = builtin_str(name)
+    getter.__name__ = name
     return cached_property(getter)
 
 
-class Cache(object):
-    """Class that manages cache locations of a dvc repo.
+class Cache:
+    """Class that manages cache locations of a DVC repo.
 
     Args:
         repo (dvc.repo.Repo): repo instance that this cache belongs to.
@@ -73,42 +53,57 @@ class Cache(object):
         from dvc.remote import Remote
 
         self.repo = repo
+        self.config = config = repo.config["cache"]
 
-        self.config = config = repo.config.config[Config.SECTION_CACHE]
-        local = config.get(Config.SECTION_CACHE_LOCAL)
+        local = config.get("local")
 
         if local:
-            name = Config.SECTION_REMOTE_FMT.format(local)
-            settings = repo.config.config[name]
+            settings = {"name": local}
         else:
-            default_cache_dir = os.path.join(repo.dvc_dir, self.CACHE_DIR)
-            cache_dir = config.get(Config.SECTION_CACHE_DIR, default_cache_dir)
-            cache_type = config.get(Config.SECTION_CACHE_TYPE)
-            protected = config.get(Config.SECTION_CACHE_PROTECTED)
-            shared = config.get(Config.SECTION_CACHE_SHARED)
-
-            settings = {
-                Config.PRIVATE_CWD: config.get(
-                    Config.PRIVATE_CWD, repo.dvc_dir
-                ),
-                Config.SECTION_REMOTE_URL: cache_dir,
-                Config.SECTION_CACHE_TYPE: cache_type,
-                Config.SECTION_CACHE_PROTECTED: protected,
-                Config.SECTION_CACHE_SHARED: shared,
-            }
+            settings = {**config, "url": config["dir"]}
 
         self.local = Remote(repo, **settings)
 
-    s3 = _make_remote_property(Config.SECTION_CACHE_S3)
-    gs = _make_remote_property(Config.SECTION_CACHE_GS)
-    ssh = _make_remote_property(Config.SECTION_CACHE_SSH)
-    hdfs = _make_remote_property(Config.SECTION_CACHE_HDFS)
-    azure = _make_remote_property(Config.SECTION_CACHE_AZURE)
+    s3 = _make_remote_property("s3")
+    gs = _make_remote_property("gs")
+    ssh = _make_remote_property("ssh")
+    hdfs = _make_remote_property("hdfs")
+    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:
+    def __init__(self):
+        self._items = defaultdict(lambda: defaultdict(NamedCacheItem))
         self.external = defaultdict(set)
 
     @classmethod
@@ -121,7 +116,18 @@ 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)
@@ -129,11 +135,32 @@ 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

@@ -1,43 +1,44 @@
-"""Command line interface for dvc."""
-from __future__ import print_function
-from __future__ import unicode_literals
-
+"""DVC command line interface"""
 import argparse
 import logging
 import sys
 
-import dvc.command.add as add
-import dvc.command.cache as cache
-import dvc.command.checkout as checkout
-import dvc.command.commit as commit
-import dvc.command.config as config
-import dvc.command.daemon as daemon
-import dvc.command.data_sync as data_sync
-import dvc.command.destroy as destroy
-import dvc.command.diff as diff
-import dvc.command.gc as gc
-import dvc.command.get as get
-import dvc.command.get_url as get_url
-import dvc.command.imp as imp
-import dvc.command.imp_url as imp_url
-import dvc.command.init as init
-import dvc.command.install as install
-import dvc.command.lock as lock
-import dvc.command.metrics as metrics
-import dvc.command.move as move
-import dvc.command.pipeline as pipeline
-import dvc.command.remote as remote
-import dvc.command.remove as remove
-import dvc.command.repro as repro
-import dvc.command.root as root
-import dvc.command.run as run
-import dvc.command.tag as tag
-import dvc.command.unprotect as unprotect
-import dvc.command.update as update
-import dvc.command.version as version
-from dvc.command.base import fix_subparsers
-from dvc.exceptions import DvcParserError
-
+from .command import (
+    add,
+    cache,
+    checkout,
+    commit,
+    config,
+    daemon,
+    data_sync,
+    destroy,
+    diff,
+    gc,
+    get,
+    get_url,
+    git_hook,
+    imp,
+    imp_url,
+    init,
+    install,
+    lock,
+    ls,
+    metrics,
+    move,
+    params,
+    pipeline,
+    plots,
+    remote,
+    remove,
+    repro,
+    root,
+    run,
+    unprotect,
+    update,
+    version,
+)
+from .command.base import fix_subparsers
+from .exceptions import DvcParserError
 
 logger = logging.getLogger(__name__)
 
@@ -61,16 +62,19 @@ COMMANDS = [
     remote,
     cache,
     metrics,
+    params,
     install,
     root,
+    ls,
     lock,
     pipeline,
     daemon,
     commit,
-    tag,
     diff,
     version,
     update,
+    git_hook,
+    plots,
 ]
 
 
@@ -92,7 +96,7 @@ class DvcParser(argparse.ArgumentParser):
 
 class VersionAction(argparse.Action):  # pragma: no cover
     # pylint: disable=too-few-public-methods
-    """Shows dvc version and exits."""
+    """Shows DVC version and exits."""
 
     def __call__(self, parser, namespace, values, option_string=None):
         from dvc import __version__
@@ -173,7 +177,7 @@ def parse_args(argv=None):
         title="Available Commands",
         metavar="COMMAND",
         dest="cmd",
-        help="Use dvc COMMAND --help for command-specific help.",
+        help="Use `dvc COMMAND --help` for command-specific help.",
     )
 
     fix_subparsers(subparsers)

dvc/command/add.py

@@ -1,13 +1,8 @@
-from __future__ import unicode_literals
-
 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.exceptions import RecursiveAddingWhileUsingFilename
-
+from dvc.command.base import CmdBase, append_doc_link
+from dvc.exceptions import DvcException, RecursiveAddingWhileUsingFilename
 
 logger = logging.getLogger(__name__)
 
@@ -58,6 +53,7 @@ def add_parser(subparsers, parent_parser):
         "-f",
         "--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."

dvc/command/base.py

@@ -1,8 +1,5 @@
-from __future__ import unicode_literals
-
 import logging
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -14,11 +11,8 @@ def fix_subparsers(subparsers):
         Args:
             subparsers: subparsers to fix.
     """
-    from dvc.utils.compat import is_py3
-
-    if is_py3:  # pragma: no cover
-        subparsers.required = True
-        subparsers.dest = "cmd"
+    subparsers.required = True
+    subparsers.dest = "cmd"
 
 
 def append_doc_link(help_message, path):
@@ -32,7 +26,7 @@ def append_doc_link(help_message, path):
     )
 
 
-class CmdBase(object):
+class CmdBase:
     def __init__(self, args):
         from dvc.repo import Repo
         from dvc.updater import Updater
@@ -40,18 +34,17 @@ class CmdBase(object):
         self.repo = Repo()
         self.config = self.repo.config
         self.args = args
-        hardlink_lock = self.config.config["core"].get("hardlink_lock", False)
-        updater = Updater(self.repo.dvc_dir, hardlink_lock=hardlink_lock)
+        hardlink_lock = self.config["core"].get("hardlink_lock", False)
+        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
     def run(self):

dvc/command/cache.py

@@ -1,20 +1,13 @@
-from __future__ import unicode_literals
-
 import argparse
 
-from dvc.cache import CacheConfig
-from dvc.command.base import append_doc_link
-from dvc.command.base import fix_subparsers
+from dvc.command.base import append_doc_link, fix_subparsers
 from dvc.command.config import CmdConfig
 
 
 class CmdCacheDir(CmdConfig):
-    def __init__(self, args):
-        super(CmdCacheDir, self).__init__(args)
-        self.cache_config = CacheConfig(self.config)
-
     def run(self):
-        self.cache_config.set_dir(self.args.value, level=self.args.level)
+        with self.config.edit(level=self.args.level) as edit:
+            edit["cache"]["dir"] = self.args.value
         return 0
 
 
@@ -32,7 +25,8 @@ def add_parser(subparsers, parent_parser):
     )
 
     cache_subparsers = cache_parser.add_subparsers(
-        dest="cmd", help="Use dvc cache CMD --help for command-specific help."
+        dest="cmd",
+        help="Use `dvc cache CMD --help` for command-specific " "help.",
     )
 
     fix_subparsers(cache_subparsers)

dvc/command/checkout.py

@@ -1,20 +1,67 @@
-from __future__ import unicode_literals
-
 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.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
 
 
@@ -28,6 +75,12 @@ 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",

dvc/command/commit.py

@@ -1,13 +1,9 @@
-from __future__ import unicode_literals
-
 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__)
 
 
@@ -49,7 +45,7 @@ def add_parser(subparsers, parent_parser):
         "--force",
         action="store_true",
         default=False,
-        help="Commit even if checksums for dependencies/outputs changed.",
+        help="Commit even if hash value for dependencies/outputs changed.",
     )
     commit_parser.add_argument(
         "-d",

dvc/command/config.py

@@ -1,36 +1,36 @@
-from __future__ import unicode_literals
-
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import CmdBaseNoRepo
-from dvc.config import Config
-
+from dvc.command.base import CmdBaseNoRepo, append_doc_link
+from dvc.config import Config, ConfigError
 
 logger = logging.getLogger(__name__)
 
 
 class CmdConfig(CmdBaseNoRepo):
     def __init__(self, args):
-        super(CmdConfig, self).__init__(args)
+        super().__init__(args)
 
         self.config = Config(validate=False)
 
     def run(self):
         section, opt = self.args.name.lower().strip().split(".", 1)
 
-        if self.args.unset:
-            self.config.unset(section, opt, level=self.args.level)
-        elif self.args.value is None:
-            logger.info(self.config.get(section, opt, level=self.args.level))
-        else:
-            self.config.set(
-                section, opt, self.args.value, level=self.args.level
-            )
+        if self.args.value is None and not self.args.unset:
+            conf = self.config.load_one(self.args.level)
+            self._check(conf, section, opt)
+            logger.info(conf[section][opt])
+            return 0
 
-        is_write = self.args.unset or self.args.value is not None
-        if is_write and self.args.name == "cache.type":
+        with self.config.edit(self.args.level) as conf:
+            if self.args.unset:
+                self._check(conf, section, opt)
+                del conf[section][opt]
+            else:
+                self._check(conf, section)
+                conf[section][opt] = self.args.value
+
+        if self.args.name == "cache.type":
             logger.warning(
                 "You have changed the 'cache.type' option. This doesn't update"
                 " any existing workspace file links, but it can be done with:"
@@ -39,30 +39,39 @@ class CmdConfig(CmdBaseNoRepo):
 
         return 0
 
+    def _check(self, conf, section, opt=None):
+        if section not in conf:
+            msg = "section {} doesn't exist"
+            raise ConfigError(msg.format(self.args.name))
+
+        if opt and opt not in conf[section]:
+            msg = "option {} doesn't exist"
+            raise ConfigError(msg.format(self.args.name))
+
 
 parent_config_parser = argparse.ArgumentParser(add_help=False)
 parent_config_parser.add_argument(
     "--global",
     dest="level",
     action="store_const",
-    const=Config.LEVEL_GLOBAL,
+    const="global",
     help="Use global config.",
 )
 parent_config_parser.add_argument(
     "--system",
     dest="level",
     action="store_const",
-    const=Config.LEVEL_SYSTEM,
+    const="system",
     help="Use system config.",
 )
 parent_config_parser.add_argument(
     "--local",
     dest="level",
     action="store_const",
-    const=Config.LEVEL_LOCAL,
+    const="local",
     help="Use local config.",
 )
-parent_config_parser.set_defaults(level=Config.LEVEL_REPO)
+parent_config_parser.set_defaults(level="repo")
 
 
 def add_parser(subparsers, parent_parser):

dvc/command/daemon.py

@@ -1,7 +1,4 @@
-from __future__ import unicode_literals
-
-from dvc.command.base import CmdBaseNoRepo
-from dvc.command.base import fix_subparsers
+from dvc.command.base import CmdBaseNoRepo, fix_subparsers
 
 
 class CmdDaemonBase(CmdBaseNoRepo):
@@ -17,11 +14,10 @@ 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.config.get("core", {}).get(
-            "hardlink_lock", False
-        )
-        updater = Updater(dvc_dir, hardlink_lock=hardlink_lock)
+        hardlink_lock = config.get("core", {}).get("hardlink_lock", False)
+        updater = Updater(tmp_dir, hardlink_lock=hardlink_lock)
         updater.fetch(detach=False)
 
         return 0
@@ -46,7 +42,8 @@ def add_parser(subparsers, parent_parser):
     )
 
     daemon_subparsers = daemon_parser.add_subparsers(
-        dest="cmd", help="Use dvc daemon CMD --help for command-specific help."
+        dest="cmd",
+        help="Use `dvc daemon CMD --help` for command-specific " "help.",
     )
 
     fix_subparsers(daemon_subparsers)

dvc/command/data_sync.py

@@ -1,40 +1,45 @@
-from __future__ import unicode_literals
-
 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.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
 
 
@@ -47,13 +52,15 @@ 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
 
 
@@ -66,13 +73,15 @@ 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
 
 
@@ -80,27 +89,31 @@ 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.",
     )
 
-    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",
@@ -110,7 +123,7 @@ 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",
@@ -126,6 +139,12 @@ 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",
@@ -147,10 +166,16 @@ 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=argparse.SUPPRESS,
+    )
     pull_parser.set_defaults(func=CmdDataPull)
 
     # Push
-    PUSH_HELP = "Push data files to a DVC remote storage."
+    PUSH_HELP = "Upload tracked files or directories to remote storage."
 
     push_parser = subparsers.add_parser(
         "push",
@@ -160,7 +185,7 @@ 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",
@@ -176,6 +201,12 @@ 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",
@@ -188,12 +219,21 @@ 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=argparse.SUPPRESS,
     )
     push_parser.set_defaults(func=CmdDataPush)
 
     # Fetch
-    FETCH_HELP = "Fetch data files from a DVC remote storage."
+    FETCH_HELP = (
+        "Get tracked files or directories from remote storage"
+        " into the cache."
+    )
 
     fetch_parser = subparsers.add_parser(
         "fetch",
@@ -203,7 +243,10 @@ 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 +262,12 @@ 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 +282,12 @@ 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=argparse.SUPPRESS,
+    )
     fetch_parser.set_defaults(func=CmdDataFetch)
 
     # Status
@@ -266,7 +321,10 @@ 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 +342,13 @@ 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 +356,12 @@ 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.set_defaults(func=CmdDataStatus)

dvc/command/destroy.py

@@ -1,14 +1,10 @@
-from __future__ import unicode_literals
-
 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__)
 
 

dvc/command/diff.py

@@ -1,172 +1,173 @@
-from __future__ import unicode_literals
-
 import argparse
+import json
 import logging
+import os
 
-import humanize
-import inflect
-from funcy import compact
+import colorama
 
-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__)
 
 
+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 _print_size(size):
-        if size < 0:
-            change = "decreased by {}"
-        elif size > 0:
-            change = "increased by {}"
-        else:
-            change = "not changed"
-        natur_size = humanize.naturalsize(abs(size))
-        return change.format(natur_size)
+    def _format(diff):
+        """
+        Given a diff structure, generate a string of paths separated
+        by new lines and grouped together by their state.
 
-    @staticmethod
-    def _get_md5_string(sign, file_name, checksum):
-        sample_msg = ""
-        if file_name:
-            sample_msg = "{}{} with md5 {}\n"
-            sample_msg = sample_msg.format(sign, file_name, checksum)
-        return sample_msg
+        A group's header is colored and its entries are sorted to enhance
+        readability, for example:
 
-    @classmethod
-    def _get_dir_changes(cls, dct):
-        import dvc.repo.diff as diff
+            Added:
+                another_file.txt
+                backup.tar
+                dir/
+                dir/1
 
-        engine = inflect.engine()
-        changes_msg = (
-            "{} {} untouched, {} {} modified, {} {} added, "
-            "{} {} deleted, size was {}"
+        An example of a diff formatted when entries contain hash:
+
+            Added:
+                d3b07384 foo
+
+            Modified:
+                c157a790..f98bf6f1 bar
+
+        If a group has no entries, it won't be included in the result.
+
+        At the bottom, include a summary with the number of files per state.
+        """
+
+        def _digest(checksum):
+            if type(checksum) is str:
+                return checksum[0:8]
+            return "{}..{}".format(checksum["old"][0:8], checksum["new"][0:8])
+
+        colors = {
+            "added": colorama.Fore.GREEN,
+            "modified": colorama.Fore.YELLOW,
+            "deleted": colorama.Fore.RED,
+        }
+
+        summary = {}
+        groups = []
+
+        for state in ["added", "deleted", "modified"]:
+            summary[state] = 0
+            entries = diff[state]
+
+            if not entries:
+                continue
+
+            content = []
+
+            for entry in entries:
+                path = entry["path"]
+                checksum = entry.get("hash")
+                summary[state] += 1 if not path.endswith(os.sep) else 0
+                content.append(
+                    "{space}{checksum}{separator}{path}".format(
+                        space="    ",
+                        checksum=_digest(checksum) if checksum else "",
+                        separator="  " if checksum else "",
+                        path=entry["path"],
+                    )
+                )
+
+            groups.append(
+                "{color}{header}{nc}:\n{content}".format(
+                    color=colors[state],
+                    header=state.capitalize(),
+                    nc=colorama.Fore.RESET,
+                    content="\n".join(content),
+                )
+            )
+
+        groups.append(
+            "files summary: {added} added, {deleted} deleted,"
+            " {modified} modified".format_map(summary)
         )
-        changes_msg = changes_msg.format(
-            dct[diff.DIFF_IDENT],
-            engine.plural("file", dct[diff.DIFF_IDENT]),
-            dct[diff.DIFF_CHANGE],
-            engine.plural("file", dct[diff.DIFF_CHANGE]),
-            dct[diff.DIFF_NEW],
-            engine.plural("file", dct[diff.DIFF_NEW]),
-            dct[diff.DIFF_DEL],
-            engine.plural("file", dct[diff.DIFF_DEL]),
-            cls._print_size(dct[diff.DIFF_SIZE]),
-        )
-        return changes_msg
 
-    @classmethod
-    def _get_file_changes(cls, dct):
-        import dvc.repo.diff as diff
-
-        if (
-            dct.get(diff.DIFF_OLD_FILE)
-            and dct.get(diff.DIFF_NEW_FILE)
-            and dct[diff.DIFF_SIZE] == 0
-        ):
-            msg = "file size was not changed"
-        elif dct.get(diff.DIFF_NEW_FILE):
-            msg = "added file with size {}".format(
-                humanize.naturalsize(dct[diff.DIFF_SIZE])
-            )
-        elif dct.get(diff.DIFF_OLD_FILE):
-            msg = "deleted file with size {}".format(
-                humanize.naturalsize(abs(dct[diff.DIFF_SIZE]))
-            )
-        else:
-            msg = "file was modified, file size {}".format(
-                cls._print_size(dct[diff.DIFF_SIZE])
-            )
-        return msg
-
-    @classmethod
-    def _get_royal_changes(cls, dct):
-        import dvc.repo.diff as diff
-
-        if dct[diff.DIFF_SIZE] != diff.DIFF_SIZE_UNKNOWN:
-            if dct.get("is_dir"):
-                return cls._get_dir_changes(dct)
-            else:
-                return cls._get_file_changes(dct)
-        return "size is ?"
-
-    @classmethod
-    def _show(cls, diff_dct):
-        import dvc.repo.diff as diff
-
-        msg = "dvc diff from {} to {}".format(
-            diff_dct[diff.DIFF_A_REF], diff_dct[diff.DIFF_B_REF]
-        )
-        if diff_dct.get(diff.DIFF_EQUAL):
-            logger.info(msg)
-            return
-        for dct in diff_dct[diff.DIFF_LIST]:
-            msg += "\n\ndiff for '{}'\n".format(dct[diff.DIFF_TARGET])
-            msg += cls._get_md5_string(
-                "-",
-                dct.get(diff.DIFF_OLD_FILE),
-                dct.get(diff.DIFF_OLD_CHECKSUM),
-            )
-            msg += cls._get_md5_string(
-                "+",
-                dct.get(diff.DIFF_NEW_FILE),
-                dct.get(diff.DIFF_NEW_CHECKSUM),
-            )
-            msg += "\n"
-            msg += cls._get_royal_changes(dct)
-        logger.info(msg)
-        return msg
+        return "\n\n".join(groups)
 
     def run(self):
         try:
-            msg = self.repo.diff(
-                self.args.a_ref, target=self.args.target, b_ref=self.args.b_ref
-            )
-            self._show(msg)
+            diff = self.repo.diff(self.args.a_rev, self.args.b_rev)
+
+            if not self.args.show_hash:
+                for _, entries in diff.items():
+                    for entry in entries:
+                        del entry["hash"]
+
+            if self.args.show_json:
+                logger.info(json.dumps(diff))
+            elif self.args.show_md:
+                logger.info(_show_md(diff))
+            elif diff:
+                logger.info(self._format(diff))
+
         except DvcException:
-            msg = "failed to get 'diff {}'"
-            args = " ".join(
-                compact([self.args.target, self.args.a_ref, self.args.b_ref])
-            )
-            msg = msg.format(args)
-            logger.exception(msg)
+            logger.exception("failed to get diff")
             return 1
         return 0
 
 
 def add_parser(subparsers, parent_parser):
     DIFF_DESCRIPTION = (
-        "Show diff of a data file or a directory that is under DVC control.\n"
-        "Some basic statistics summary, how many files were deleted/changed."
+        "Show added, modified, or deleted data between commits in the DVC"
+        " repository, or between a commit and the workspace."
     )
-    DIFF_HELP = "Show a diff of a DVC controlled data file or a directory."
     diff_parser = subparsers.add_parser(
         "diff",
         parents=[parent_parser],
         description=append_doc_link(DIFF_DESCRIPTION, "diff"),
-        help=DIFF_HELP,
+        help=DIFF_DESCRIPTION,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     diff_parser.add_argument(
-        "-t",
-        "--target",
-        help=(
-            "Source path to a data file or directory. Default None. "
-            "If not specified, compares all files and directories "
-            "that are under DVC control in the current working space."
-        ),
+        "a_rev",
+        help="Old Git commit to compare (defaults to HEAD)",
+        nargs="?",
+        default="HEAD",
     )
     diff_parser.add_argument(
-        "a_ref", help="Git reference from which diff calculates"
-    )
-    diff_parser.add_argument(
-        "b_ref",
-        help=(
-            "Git reference until which diff calculates, if omitted "
-            "diff shows the difference between current HEAD and a_ref"
-        ),
+        "b_rev",
+        help=("New Git commit to compare (defaults to the current workspace)"),
         nargs="?",
     )
+    diff_parser.add_argument(
+        "--show-json",
+        help="Format the output into a JSON",
+        action="store_true",
+        default=False,
+    )
+    diff_parser.add_argument(
+        "--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/gc.py

@@ -1,19 +1,24 @@
-from __future__ import unicode_literals
-
 import argparse
 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"
@@ -49,15 +54,16 @@ class CmdGC(CmdBase):
             force=self.args.force,
             jobs=self.args.jobs,
             repos=self.args.repos,
+            workspace=self.args.workspace,
         )
         return 0
 
 
 def add_parser(subparsers, parent_parser):
-    GC_HELP = "Collect unused data from DVC cache or a remote storage."
+    GC_HELP = "Garbage collect unused objects from cache or remote storage."
     GC_DESCRIPTION = (
-        "Deletes all files in the cache or a remote which are not in\n"
-        "use by the specified git references (defaults to just HEAD)."
+        "Removes all files in the cache or a remote which are not in\n"
+        "use by the specified Git revisions (defaults to just HEAD)."
     )
     gc_parser = subparsers.add_parser(
         "gc",
@@ -66,25 +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 (working tree).",
+    )
     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",
@@ -94,7 +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",
@@ -104,7 +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",
@@ -115,5 +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

@@ -1,18 +1,35 @@
-from __future__ import unicode_literals
-
 import argparse
 import logging
 
-from .base import append_doc_link
-from .base import CmdBaseNoRepo
 from dvc.exceptions import DvcException
 
+from .base import CmdBaseNoRepo, append_doc_link
 
 logger = logging.getLogger(__name__)
 
 
 class CmdGet(CmdBaseNoRepo):
+    def _show_url(self):
+        from dvc.api import get_url
+
+        try:
+            url = get_url(
+                self.args.path, repo=self.args.url, rev=self.args.rev
+            )
+            logger.info(url)
+        except DvcException:
+            logger.exception("failed to show URL")
+            return 1
+
+        return 0
+
     def run(self):
+        if self.args.show_url:
+            return self._show_url()
+
+        return self._get_file_from_repo()
+
+    def _get_file_from_repo(self):
         from dvc.repo import Repo
 
         try:
@@ -33,7 +50,7 @@ class CmdGet(CmdBaseNoRepo):
 
 
 def add_parser(subparsers, parent_parser):
-    GET_HELP = "Download/copy files or directories from DVC repository."
+    GET_HELP = "Download file or directory tracked by DVC or by Git."
     get_parser = subparsers.add_parser(
         "get",
         parents=[parent_parser],
@@ -42,18 +59,28 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     get_parser.add_argument(
-        "url", help="URL of Git repository with DVC project to download from."
+        "url", help="Location of DVC or Git repository to download from"
     )
     get_parser.add_argument(
-        "path", help="Path to a file or directory within a DVC repository."
+        "path", help="Path to a file or directory within the repository"
     )
     get_parser.add_argument(
         "-o",
         "--out",
         nargs="?",
-        help="Destination path to copy/download files to.",
+        help="Destination path to download files to",
+        metavar="<path>",
     )
     get_parser.add_argument(
-        "--rev", nargs="?", help="DVC repository git revision."
+        "--rev",
+        nargs="?",
+        help="Git revision (e.g. SHA, branch, tag)",
+        metavar="<commit>",
+    )
+    get_parser.add_argument(
+        "--show-url",
+        action="store_true",
+        help="Print the storage location (URL) the target data would be "
+        "downloaded from, and exit.",
     )
     get_parser.set_defaults(func=CmdGet)

dvc/command/get_url.py

@@ -1,12 +1,9 @@
-from __future__ import unicode_literals
-
 import argparse
 import logging
 
-from .base import append_doc_link
-from .base import CmdBaseNoRepo
 from dvc.exceptions import DvcException
 
+from .base import CmdBaseNoRepo, append_doc_link
 
 logger = logging.getLogger(__name__)
 
@@ -19,7 +16,7 @@ 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
 
 

dvc/command/git_hook.py

@@ -0,0 +1,112 @@
+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()
+
+
+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

@@ -1,13 +1,9 @@
-from __future__ import unicode_literals
-
 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__)
 
 
@@ -32,7 +28,8 @@ class CmdImport(CmdBase):
 
 def add_parser(subparsers, parent_parser):
     IMPORT_HELP = (
-        "Download data from DVC repository and take it under DVC control."
+        "Download file or directory tracked by DVC or by Git "
+        "into the workspace, and track it."
     )
 
     import_parser = subparsers.add_parser(
@@ -43,15 +40,22 @@ def add_parser(subparsers, parent_parser):
         formatter_class=argparse.RawTextHelpFormatter,
     )
     import_parser.add_argument(
-        "url", help="URL of Git repository with DVC project to download from."
+        "url", help="Location of DVC or Git repository to download from"
     )
     import_parser.add_argument(
-        "path", help="Path to data within DVC repository."
+        "path", help="Path to a file or directory within the repository"
     )
     import_parser.add_argument(
-        "-o", "--out", nargs="?", help="Destination path to put data to."
+        "-o",
+        "--out",
+        nargs="?",
+        help="Destination path to download files to",
+        metavar="<path>",
     )
     import_parser.add_argument(
-        "--rev", nargs="?", help="DVC repository git revision."
+        "--rev",
+        nargs="?",
+        help="Git revision (e.g. SHA, branch, tag)",
+        metavar="<commit>",
     )
     import_parser.set_defaults(func=CmdImport)

dvc/command/imp_url.py

@@ -1,13 +1,9 @@
-from __future__ import unicode_literals
-
 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__)
 
 
@@ -61,6 +57,9 @@ def add_parser(subparsers, parent_parser):
         "out", nargs="?", help="Destination path to put files to."
     )
     import_parser.add_argument(
-        "-f", "--file", help="Specify name of the DVC-file it generates."
+        "-f",
+        "--file",
+        help="Specify name of the DVC-file this command will generate.",
+        metavar="<filename>",
     )
     import_parser.set_defaults(func=CmdImportUrl)

dvc/command/init.py

@@ -1,11 +1,7 @@
-from __future__ import unicode_literals
-
 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__)
 
@@ -17,11 +13,14 @@ 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:
-            logger.exception("failed to initiate dvc")
+            logger.exception("failed to initiate DVC")
             return 1
         return 0
 
@@ -45,8 +44,8 @@ def add_parser(subparsers, parent_parser):
         "--no-scm",
         action="store_true",
         default=False,
-        help="Initiate dvc in directory that is "
-        "not tracked by any scm tool (e.g. git).",
+        help="Initiate DVC in directory that is "
+        "not tracked by any SCM tool (e.g. Git).",
     )
     init_parser.add_argument(
         "-f",
@@ -58,4 +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

@@ -1,11 +1,7 @@
-from __future__ import unicode_literals
-
 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__)
 
@@ -13,9 +9,9 @@ logger = logging.getLogger(__name__)
 class CmdInstall(CmdBase):
     def run(self):
         try:
-            self.repo.install()
+            self.repo.install(self.args.use_pre_commit_tool)
         except Exception:
-            logger.exception("failed to install dvc hooks")
+            logger.exception("failed to install DVC Git hooks")
             return 1
         return 0
 
@@ -29,4 +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

@@ -1,13 +1,9 @@
-from __future__ import unicode_literals
-
 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__)
 
 

dvc/command/ls/__init__.py

@@ -0,0 +1,78 @@
+import argparse
+import logging
+import sys
+
+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,
+                outs_only=self.args.outs_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(
+        "--outs-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",
+    )
+    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

@@ -1,43 +1,34 @@
-from __future__ import unicode_literals
-
 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.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`
-    """
+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():
-            lines = metric if type(metric) is list else 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)
@@ -48,14 +39,23 @@ 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
@@ -63,27 +63,12 @@ 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
-
-        return 0
-
-
 class CmdMetricsAdd(CmdBase):
     def run(self):
         try:
-            self.repo.metrics.add(
-                self.args.path, self.args.type, self.args.xpath
-            )
+            self.repo.metrics.add(self.args.path)
         except DvcException:
-            msg = "failed to add metric file '{}'".format(self.args.path)
+            msg = f"failed to add metric file '{self.args.path}'"
             logger.exception(msg)
             return 1
 
@@ -95,15 +80,63 @@ class CmdMetricsRemove(CmdBase):
         try:
             self.repo.metrics.remove(self.args.path)
         except DvcException:
-            msg = "failed to remove metric file '{}'".format(self.args.path)
+            msg = f"failed to remove metric file '{self.args.path}'"
             logger.exception(msg)
             return 1
 
         return 0
 
 
+def _show_diff(diff, markdown=False):
+    from collections import OrderedDict
+
+    from dvc.utils.diff import table
+
+    rows = []
+    for fname, mdiff in diff.items():
+        sorted_mdiff = OrderedDict(sorted(mdiff.items()))
+        for metric, change in sorted_mdiff.items():
+            rows.append(
+                [
+                    fname,
+                    metric,
+                    change["new"],
+                    change.get("diff", "diff not supported"),
+                ]
+            )
+
+    return table(["Path", "Metric", "Value", "Change"], rows, markdown)
+
+
+class CmdMetricsDiff(CmdBase):
+    def run(self):
+        try:
+            diff = self.repo.metrics.diff(
+                a_rev=self.args.a_rev,
+                b_rev=self.args.b_rev,
+                targets=self.args.targets,
+                recursive=self.args.recursive,
+                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)
+                if table:
+                    logger.info(table)
+
+        except DvcException:
+            logger.exception("failed to show metrics diff")
+            return 1
+
+        return 0
+
+
 def add_parser(subparsers, parent_parser):
-    METRICS_HELP = "Commands to add, manage, collect and display metrics."
+    METRICS_HELP = "Commands to add, manage, collect, and display metrics."
 
     metrics_parser = subparsers.add_parser(
         "metrics",
@@ -115,12 +148,23 @@ def add_parser(subparsers, parent_parser):
 
     metrics_subparsers = metrics_parser.add_subparsers(
         dest="cmd",
-        help="Use dvc metrics CMD --help to display command-specific help.",
+        help="Use `dvc metrics CMD --help` to display command-specific help.",
     )
 
     fix_subparsers(metrics_subparsers)
 
-    METRICS_SHOW_HELP = "Output metric values."
+    METRICS_ADD_HELP = "Mark a DVC-tracked file as a metric."
+    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_add_parser.add_argument("path", help="Path to a metric file.")
+    metrics_add_parser.set_defaults(func=CmdMetricsAdd)
+
+    METRICS_SHOW_HELP = "Print metrics, with optional formatting."
     metrics_show_parser = metrics_subparsers.add_parser(
         "show",
         parents=[parent_parser],
@@ -131,20 +175,7 @@ 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."
-        ),
-    )
-    metrics_show_parser.add_argument(
-        "-x", "--xpath", help="json/tsv/htsv/csv/hcsv path."
+        help="Metric files or directories (see -R) to show",
     )
     metrics_show_parser.add_argument(
         "-a",
@@ -160,6 +191,12 @@ 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(
         "-R",
         "--recursive",
@@ -170,43 +207,71 @@ def add_parser(subparsers, parent_parser):
             "metric files."
         ),
     )
+    metrics_show_parser.add_argument(
+        "--show-json",
+        action="store_true",
+        default=False,
+        help="Show output in JSON format.",
+    )
     metrics_show_parser.set_defaults(func=CmdMetricsShow)
 
-    METRICS_ADD_HELP = "Tag file as a metric file."
-    metrics_add_parser = metrics_subparsers.add_parser(
-        "add",
+    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],
-        description=append_doc_link(METRICS_ADD_HELP, "metrics/add"),
-        help=METRICS_ADD_HELP,
+        description=append_doc_link(METRICS_DIFF_HELP, "metrics/diff"),
+        help=METRICS_DIFF_HELP,
         formatter_class=argparse.RawDescriptionHelpFormatter,
     )
-    metrics_add_parser.add_argument(
-        "-t", "--type", help="Type of metrics (raw/json/tsv/htsv/csv/hcsv)."
+    metrics_diff_parser.add_argument(
+        "a_rev", nargs="?", help="Old Git commit to compare (defaults to HEAD)"
     )
-    metrics_add_parser.add_argument(
-        "-x", "--xpath", help="json/tsv/htsv/csv/hcsv path."
+    metrics_diff_parser.add_argument(
+        "b_rev",
+        nargs="?",
+        help=("New Git commit to compare (defaults to the current workspace)"),
     )
-    metrics_add_parser.add_argument("path", help="Path to a metric file.")
-    metrics_add_parser.set_defaults(func=CmdMetricsAdd)
+    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."
+        ),
+        metavar="<paths>",
+    )
+    metrics_diff_parser.add_argument(
+        "-R",
+        "--recursive",
+        action="store_true",
+        default=False,
+        help=(
+            "If any target is a directory, recursively search and process "
+            "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.set_defaults(func=CmdMetricsDiff)
 
-    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_HELP = "Remove metric mark on a DVC-tracked file."
     metrics_remove_parser = metrics_subparsers.add_parser(
         "remove",
         parents=[parent_parser],

dvc/command/move.py

@@ -1,13 +1,9 @@
-from __future__ import unicode_literals
-
 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__)
 
 

dvc/command/params.py

@@ -0,0 +1,103 @@
+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):
+    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():
+            rows.append([fname, param, change["old"], change["new"]])
+
+    return table(["Path", "Param", "Old", "New"], 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)
+                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.set_defaults(func=CmdParamsDiff)

dvc/command/pipeline.py

@@ -1,15 +1,8 @@
-from __future__ import unicode_literals
-
 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.command.base import CmdBase, append_doc_link, fix_subparsers
 from dvc.exceptions import DvcException
-from dvc.utils import relpath
-from dvc.utils.compat import str
-
 
 logger = logging.getLogger(__name__)
 
@@ -17,73 +10,89 @@ logger = logging.getLogger(__name__)
 class CmdPipelineShow(CmdBase):
     def _show(self, target, commands, outs, locked):
         import networkx
-        from dvc.stage import Stage
+        from dvc import dvcfile
+        from dvc.utils import parse_target
 
-        stage = Stage.load(self.repo, target)
+        path, name = parse_target(target)
+        stage = dvcfile.Dvcfile(self.repo, path).stages[name]
         G = self.repo.graph
-        stages = networkx.get_node_attributes(G, "stage")
-        node = relpath(stage.path, self.repo.root_dir)
-        nodes = networkx.dfs_postorder_nodes(G, node)
-
+        stages = networkx.dfs_postorder_nodes(G, stage)
         if locked:
-            nodes = [n for n in nodes if stages[n].locked]
+            stages = [s for s in stages if s.locked]
 
-        for n in nodes:
-            if commands:
-                if stages[n].cmd is None:
-                    continue
-                logger.info(stages[n].cmd)
-            elif outs:
-                for out in stages[n].outs:
-                    logger.info(str(out))
-            else:
-                logger.info(n)
-
-    def __build_graph(self, target, commands, outs):
-        import networkx
-        from dvc.stage import Stage
-        from dvc.repo.graph import get_pipeline
-
-        stage = Stage.load(self.repo, target)
-        node = relpath(stage.path, self.repo.root_dir)
-
-        G = get_pipeline(self.repo.pipelines, node)
-        stages = networkx.get_node_attributes(G, "stage")
-
-        nodes = []
-        for n in G:
-            stage = stages[n]
+        for stage in stages:
             if commands:
                 if stage.cmd is None:
                     continue
-                nodes.append(stage.cmd)
+                logger.info(stage.cmd)
             elif outs:
                 for out in stage.outs:
-                    nodes.append(str(out))
+                    logger.info(str(out))
             else:
-                nodes.append(stage.relpath)
+                logger.info(stage.addressing)
+
+    @staticmethod
+    def _build_output_graph(G, target_stage):
+        import networkx
+        from itertools import product
+
+        nodes = {str(out) for out in target_stage.outs}
+        edges = []
+
+        for from_stage, to_stage in networkx.edge_dfs(G, target_stage):
+            from_stage_deps = {dep.path_info.parts for dep in from_stage.deps}
+            to_outs = {
+                to_out
+                for to_out in to_stage.outs
+                if to_out.path_info.parts in from_stage_deps
+            }
+            from_outs = {
+                from_out
+                for from_out in from_stage.outs
+                if str(from_out) in nodes
+            }
+            nodes |= {str(to_out) for to_out in to_outs}
+            for from_out, to_out in product(from_outs, to_outs):
+                edges.append((str(from_out), str(to_out)))
+        return nodes, edges
+
+    def _build_graph(self, target, commands=False, outs=False):
+        import networkx
+        from dvc import dvcfile
+        from dvc.repo.graph import get_pipeline
+        from dvc.utils import parse_target
+
+        path, name = parse_target(target)
+        target_stage = dvcfile.Dvcfile(self.repo, path).stages[name]
+        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 not outs:
+                nodes.add(stage.addressing)
 
         edges = []
-        for e in G.edges():
-            from_stage = stages[e[0]]
-            to_stage = stages[e[1]]
+        for from_stage, to_stage in networkx.edge_dfs(G, target_stage):
             if commands:
                 if to_stage.cmd is None:
                     continue
                 edges.append((from_stage.cmd, to_stage.cmd))
-            elif outs:
-                for from_out in from_stage.outs:
-                    for to_out in to_stage.outs:
-                        edges.append((str(from_out), str(to_out)))
-            else:
-                edges.append((from_stage.relpath, to_stage.relpath))
+            elif not outs:
+                edges.append((from_stage.addressing, to_stage.addressing))
 
-        return nodes, edges, networkx.is_tree(G)
+        if outs:
+            nodes, edges = self._build_output_graph(G, target_stage)
+
+        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)
+        nodes, edges, _ = self._build_graph(target, commands, outs)
 
         if not nodes:
             return
@@ -93,7 +102,7 @@ class CmdPipelineShow(CmdBase):
     def _show_dependencies_tree(self, target, commands, outs):
         from treelib import Tree
 
-        nodes, edges, is_tree = self.__build_graph(target, commands, outs)
+        nodes, edges, is_tree = self._build_graph(target, commands, outs)
         if not nodes:
             return
         if not is_tree:
@@ -114,24 +123,26 @@ class CmdPipelineShow(CmdBase):
             observe_list.pop(0)
         tree.show()
 
-    def __write_dot(self, target, commands, outs):
-        from dvc.utils.compat import StringIO
+    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, _ = 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 = StringIO()
+        dot_file = io.StringIO()
         write_dot(simple_g, dot_file)
         logger.info(dot_file.getvalue())
 
     def run(self):
+        from dvc.dvcfile import DVC_FILE
+
         if not self.args.targets:
-            self.args.targets = self.default_targets
+            self.args.targets = [DVC_FILE]
 
         for target in self.args.targets:
             try:
@@ -140,9 +151,7 @@ class CmdPipelineShow(CmdBase):
                         target, self.args.commands, self.args.outs
                     )
                 elif self.args.dot:
-                    self.__write_dot(
-                        target, self.args.commands, self.args.outs
-                    )
+                    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
@@ -155,7 +164,7 @@ class CmdPipelineShow(CmdBase):
                         self.args.locked,
                     )
             except DvcException:
-                msg = "failed to show pipeline for '{}'".format(target)
+                msg = f"failed to show pipeline for '{target}'"
                 logger.exception(msg)
                 return 1
         return 0
@@ -163,14 +172,11 @@ class CmdPipelineShow(CmdBase):
 
 class CmdPipelineList(CmdBase):
     def run(self):
-        import networkx
-
         pipelines = self.repo.pipelines
-        for p in pipelines:
-            stages = networkx.get_node_attributes(p, "stage")
-            for stage in stages:
-                logger.info(stage)
-            if len(stages) != 0:
+        for pipeline in pipelines:
+            for stage in pipeline:
+                logger.info(stage.addressing)
+            if len(pipeline) != 0:
                 logger.info("=" * 80)
         logger.info("{} pipelines total".format(len(pipelines)))
 
@@ -189,12 +195,22 @@ def add_parser(subparsers, parent_parser):
 
     pipeline_subparsers = pipeline_parser.add_subparsers(
         dest="cmd",
-        help="Use dvc pipeline CMD --help for command-specific help.",
+        help="Use `dvc pipeline CMD --help` for command-specific help.",
     )
 
     fix_subparsers(pipeline_subparsers)
 
-    PIPELINE_SHOW_HELP = "Show pipelines."
+    PIPELINE_LIST_HELP = "List connected groups of stages (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)
+
+    PIPELINE_SHOW_HELP = "Show stages in a pipeline."
     pipeline_show_parser = pipeline_subparsers.add_parser(
         "show",
         parents=[parent_parser],
@@ -249,13 +265,3 @@ def add_parser(subparsers, parent_parser):
         "(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 +1,229 @@
+import argparse
+import logging
+import os
+
+from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
+from dvc.exceptions import DvcException
+
+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 run(self):
+        fields = None
+        jsonpath = None
+        if self.args.select:
+            if self.args.select.startswith("$"):
+                jsonpath = self.args.select
+            else:
+                fields = set(self.args.select.split(","))
+        try:
+            plots = self._func(
+                targets=self.args.targets,
+                template=self.args.template,
+                fields=fields,
+                x_field=self.args.x,
+                y_field=self.args.y,
+                path=jsonpath,
+                csv_header=not self.args.no_csv_header,
+                title=self.args.title,
+                x_title=self.args.xlab,
+                y_title=self.args.ylab,
+            )
+
+            if self.args.show_json:
+                import json
+
+                logger.info(json.dumps(plots))
+                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)
+
+
+def add_parser(subparsers, parent_parser):
+    PLOTS_HELP = (
+        "Generating plots for metrics stored in structured files "
+        "(JSON, 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 a plots image file from a metrics file."
+    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(
+        "-t",
+        "--template",
+        nargs="?",
+        default=None,
+        help="File to be injected with data.",
+    )
+    plots_show_parser.add_argument(
+        "-o", "--out", default=None, help="Destination path to save plots to.",
+    )
+    plots_show_parser.add_argument(
+        "-s",
+        "--select",
+        default=None,
+        help="Choose which field(s) or JSONPath to include in the plots.",
+    )
+    plots_show_parser.add_argument(
+        "-x", default=None, help="Field name for x axis."
+    )
+    plots_show_parser.add_argument(
+        "-y", default=None, help="Field name for y axis."
+    )
+    plots_show_parser.add_argument(
+        "--no-csv-header",
+        action="store_true",
+        default=False,
+        help="Required when CSV or TSV datafile does not have a header.",
+    )
+    plots_show_parser.add_argument(
+        "--show-json",
+        action="store_true",
+        default=False,
+        help="Show output in JSON format.",
+    )
+    plots_show_parser.add_argument("--title", default=None, help="Plot title.")
+    plots_show_parser.add_argument(
+        "--xlab", default=None, help="X axis title."
+    )
+    plots_show_parser.add_argument(
+        "--ylab", default=None, help="Y axis title."
+    )
+    plots_show_parser.add_argument(
+        "targets",
+        nargs="*",
+        help="Metrics files to visualize. Shows all plots by default.",
+    )
+    plots_show_parser.set_defaults(func=CmdPlotsShow)
+
+    PLOTS_DIFF_HELP = (
+        "Plot differences in metrics between commits in the DVC "
+        "repository, or between the last commit and the workspace."
+    )
+    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(
+        "-t",
+        "--template",
+        nargs="?",
+        default=None,
+        help="File to be injected with data.",
+    )
+    plots_diff_parser.add_argument(
+        "--targets",
+        nargs="*",
+        help="Metrics file to visualize. Shows all plots by default.",
+    )
+    plots_diff_parser.add_argument(
+        "-o", "--out", default=None, help="Destination path to save plots to.",
+    )
+    plots_diff_parser.add_argument(
+        "-s",
+        "--select",
+        default=None,
+        help="Choose which field(s) or JSONPath to include in the plot.",
+    )
+    plots_diff_parser.add_argument(
+        "-x", default=None, help="Field name for x axis."
+    )
+    plots_diff_parser.add_argument(
+        "-y", default=None, help="Field name for y axis."
+    )
+    plots_diff_parser.add_argument(
+        "--no-csv-header",
+        action="store_true",
+        default=False,
+        help="Provided CSV ot TSV datafile does not have a header.",
+    )
+    plots_diff_parser.add_argument(
+        "--show-json",
+        action="store_true",
+        default=False,
+        help="Show output in JSON format.",
+    )
+    plots_diff_parser.add_argument("--title", default=None, help="Plot title.")
+    plots_diff_parser.add_argument(
+        "--xlab", default=None, help="X axis title."
+    )
+    plots_diff_parser.add_argument(
+        "--ylab", default=None, help="Y axis title."
+    )
+    plots_diff_parser.add_argument(
+        "revisions", nargs="*", default=None, help="Git commits to plot from",
+    )
+    plots_diff_parser.set_defaults(func=CmdPlotsDiff)

dvc/command/remote.py

@@ -1,80 +1,142 @@
-from __future__ import unicode_literals
-
 import argparse
 import logging
 
-from dvc.command.base import append_doc_link
-from dvc.command.base import fix_subparsers
+from dvc.command.base import append_doc_link, fix_subparsers
 from dvc.command.config import CmdConfig
-from dvc.remote.config import RemoteConfig
+from dvc.config import ConfigError
+from dvc.utils import format_link
 
 logger = logging.getLogger(__name__)
 
 
-class CmdRemoteConfig(CmdConfig):
+class CmdRemote(CmdConfig):
     def __init__(self, args):
-        super(CmdRemoteConfig, self).__init__(args)
-        self.remote_config = RemoteConfig(self.config)
+        super().__init__(args)
+
+        if getattr(self.args, "name", None):
+            self.args.name = self.args.name.lower()
+
+    def _check_exists(self, conf):
+        if self.args.name not in conf["remote"]:
+            raise ConfigError(f"remote '{self.args.name}' doesn't exists.")
 
 
-class CmdRemoteAdd(CmdRemoteConfig):
+class CmdRemoteAdd(CmdRemote):
     def run(self):
         if self.args.default:
-            logger.info(
-                "Setting '{}' as a default remote.".format(self.args.name)
-            )
-        self.remote_config.add(
-            self.args.name,
-            self.args.url,
-            force=self.args.force,
-            default=self.args.default,
-            level=self.args.level,
-        )
+            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:
+                raise ConfigError(
+                    "remote '{}' already exists. Use `-f|--force` to "
+                    "overwrite it.".format(self.args.name)
+                )
+
+            conf["remote"][self.args.name] = {"url": self.args.url}
+            if self.args.default:
+                conf["core"]["remote"] = self.args.name
+
         return 0
 
 
-class CmdRemoteRemove(CmdRemoteConfig):
+class CmdRemoteRemove(CmdRemote):
     def run(self):
-        self.remote_config.remove(self.args.name, level=self.args.level)
+        with self.config.edit(self.args.level) as conf:
+            self._check_exists(conf)
+            del conf["remote"][self.args.name]
+
+        # Remove core.remote refs to this remote in any shadowing configs
+        for level in reversed(self.config.LEVELS):
+            with self.config.edit(level) as conf:
+                if conf["core"].get("remote") == self.args.name:
+                    del conf["core"]["remote"]
+
+            if level == self.args.level:
+                break
+
         return 0
 
 
-class CmdRemoteModify(CmdRemoteConfig):
+class CmdRemoteModify(CmdRemote):
     def run(self):
-        self.remote_config.modify(
-            self.args.name,
-            self.args.option,
-            self.args.value,
-            level=self.args.level,
-        )
+        with self.config.edit(self.args.level) as conf:
+            self._check_exists(conf)
+            conf["remote"][self.args.name][self.args.option] = self.args.value
         return 0
 
 
-class CmdRemoteDefault(CmdRemoteConfig):
+class CmdRemoteDefault(CmdRemote):
     def run(self):
+
         if self.args.name is None and not self.args.unset:
-            name = self.remote_config.get_default(level=self.args.level)
-            print(name)
+            conf = self.config.load_one(self.args.level)
+            try:
+                print(conf["core"]["remote"])
+            except KeyError:
+                logger.info("No default remote set")
+                return 1
         else:
-            self.remote_config.set_default(
-                self.args.name, unset=self.args.unset, level=self.args.level
-            )
+            with self.config.edit(self.args.level) as conf:
+                if self.args.unset:
+                    conf["core"].pop("remote", None)
+                else:
+                    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
 
 
-class CmdRemoteList(CmdRemoteConfig):
+class CmdRemoteList(CmdRemote):
     def run(self):
-        for name, url in self.remote_config.list(
-            level=self.args.level
-        ).items():
-            logger.info("{}\t{}".format(name, url))
+        conf = self.config.load_one(self.args.level)
+        for name, conf in conf["remote"].items():
+            logger.info("{}\t{}".format(name, conf["url"]))
+        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],
@@ -85,12 +147,12 @@ def add_parser(subparsers, parent_parser):
 
     remote_subparsers = remote_parser.add_subparsers(
         dest="cmd",
-        help="Use dvc remote CMD --help for " "command-specific help.",
+        help="Use `dvc remote CMD --help` for " "command-specific help.",
     )
 
     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],
@@ -101,7 +163,9 @@ def add_parser(subparsers, parent_parser):
     remote_add_parser.add_argument("name", help="Name of the remote")
     remote_add_parser.add_argument(
         "url",
-        help="URL. See full list of supported urls at " "man.dvc.org/remote",
+        help="URL. See full list of supported urls at {}".format(
+            format_link("https://man.dvc.org/remote")
+        ),
     )
     remote_add_parser.add_argument(
         "-d",
@@ -119,7 +183,7 @@ 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],
@@ -139,20 +203,7 @@ 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],
@@ -176,7 +227,7 @@ 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],
@@ -185,3 +236,27 @@ 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

@@ -1,14 +1,10 @@
-from __future__ import unicode_literals
-
 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__)
 
 
@@ -38,13 +34,13 @@ class CmdRemove(CmdBase):
                 outs_only = self._is_outs_only(target)
                 self.repo.remove(target, outs_only=outs_only)
             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 DVC-tracked files or directories."
     remove_parser = subparsers.add_parser(
         "remove",
         parents=[parent_parser],

dvc/command/repro.py

@@ -1,16 +1,12 @@
-from __future__ import unicode_literals
-
 import argparse
 import logging
 import os
 
-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.command.metrics import show_metrics
 from dvc.command.status import CmdDataStatus
 from dvc.exceptions import DvcException
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -37,10 +33,11 @@ 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:
@@ -59,7 +56,9 @@ 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],
@@ -92,6 +91,7 @@ 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",
@@ -137,7 +137,16 @@ 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

@@ -1,10 +1,7 @@
-from __future__ import unicode_literals
-
 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__)
@@ -19,7 +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

@@ -1,20 +1,14 @@
-from __future__ import unicode_literals
-
 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,
@@ -22,15 +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
 
@@ -41,21 +38,24 @@ 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,
+                overwrite=self.args.overwrite_dvcfile,
+                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,
             )
         except DvcException:
-            logger.exception("failed to run command")
+            logger.exception("")
             return 1
 
         return 0
@@ -79,7 +79,7 @@ class CmdRun(CmdBase):
         if " " not in argument or '"' in argument:
             return argument
 
-        return '"{}"'.format(argument)
+        return f'"{argument}"'
 
 
 def add_parser(subparsers, parent_parser):
@@ -97,6 +97,10 @@ 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",
@@ -104,6 +108,7 @@ def add_parser(subparsers, parent_parser):
         action="append",
         default=[],
         help="Declare output file or directory.",
+        metavar="<filename>",
     )
     run_parser.add_argument(
         "-O",
@@ -112,6 +117,15 @@ 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",
@@ -119,6 +133,7 @@ def add_parser(subparsers, parent_parser):
         action="append",
         default=[],
         help="Declare output metric file or directory.",
+        metavar="<path>",
     )
     run_parser.add_argument(
         "-M",
@@ -127,17 +142,33 @@ def add_parser(subparsers, parent_parser):
         default=[],
         help="Declare output metric file or directory "
         "(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(
+        "-f",
+        "--file",
+        help="Specify name of the DVC-file this command will generate.",
+        metavar="<filename>",
     )
     run_parser.add_argument(
         "-w",
         "--wdir",
         help="Directory within your repo to run your command in.",
+        metavar="<path>",
     )
     run_parser.add_argument(
         "--no-exec",
@@ -145,13 +176,6 @@ def add_parser(subparsers, parent_parser):
         default=False,
         help="Only create stage file without actually running it.",
     )
-    run_parser.add_argument(
-        "-y",
-        "--yes",
-        action="store_true",
-        default=False,
-        help="Deprecated, use --overwrite-dvcfile instead",
-    )
     run_parser.add_argument(
         "--overwrite-dvcfile",
         action="store_true",
@@ -159,17 +183,13 @@ def add_parser(subparsers, parent_parser):
         help="Overwrite existing DVC-file without asking for confirmation.",
     )
     run_parser.add_argument(
-        "--ignore-build-cache",
+        "--no-run-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",
@@ -183,6 +203,7 @@ 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",
@@ -190,6 +211,7 @@ 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",
@@ -197,6 +219,12 @@ 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(
         "command", nargs=argparse.REMAINDER, help="Command to execute."
     )

dvc/command/status.py

@@ -1,10 +1,6 @@
-from __future__ import unicode_literals
-
 import logging
 
 from dvc.command.data_sync import CmdDataBase
-from dvc.utils.compat import str
-
 
 logger = logging.getLogger(__name__)
 
@@ -23,7 +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):
@@ -37,7 +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):
@@ -50,7 +46,9 @@ 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:

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

@@ -1,13 +1,9 @@
-from __future__ import unicode_literals
-
 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__)
 
 
@@ -17,14 +13,17 @@ 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],

dvc/command/update.py

@@ -1,25 +1,24 @@
-from __future__ import unicode_literals
-
 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 CmdUpdate(CmdBase):
     def run(self):
         ret = 0
-        for target in self.args.targets:
-            try:
-                self.repo.update(target)
-            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
 
 
@@ -35,4 +34,17 @@ def add_parser(subparsers, parent_parser):
     update_parser.add_argument(
         "targets", nargs="+", help="DVC-files to update."
     )
+    update_parser.add_argument(
+        "--rev",
+        nargs="?",
+        help="Git revision (e.g. SHA, branch, tag)",
+        metavar="<commit>",
+    )
+    update_parser.add_argument(
+        "-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

@@ -1,24 +1,24 @@
-from __future__ import unicode_literals
-
 import argparse
 import itertools
 import logging
 import os
+import pathlib
 import platform
 import uuid
 
+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.utils.compat import pathlib
-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__)
 
@@ -27,23 +27,14 @@ class CmdVersion(CmdBaseNoRepo):
     def run(self):
         from dvc.repo import Repo
 
-        dvc_version = __version__
-        python_version = platform.python_version()
-        platform_type = platform.platform()
-        binary = is_binary()
-        info = (
-            "DVC version: {dvc_version}\n"
-            "Python version: {python_version}\n"
-            "Platform: {platform_type}\n"
-            "Binary: {binary}\n"
-            "Package: {package}\n"
-        ).format(
-            dvc_version=dvc_version,
-            python_version=python_version,
-            platform_type=platform_type,
-            binary=binary,
-            package=PKG,
-        )
+        info = [
+            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:
             repo = Repo()
@@ -54,9 +45,14 @@ class CmdVersion(CmdBaseNoRepo):
             # later decides to enable shared cache mode with
             # `dvc config cache.shared group`.
             if os.path.exists(repo.cache.local.cache_dir):
-                info += "Cache: {cache}\n".format(
-                    cache=self.get_linktype_support_info(repo)
+                info.append(
+                    "Cache: {}".format(self.get_linktype_support_info(repo))
                 )
+                if psutil:
+                    fs_type = self.get_fs_type(repo.cache.local.cache_dir)
+                    info.append(
+                        f"Filesystem type (cache directory): {fs_type}"
+                    )
             else:
                 logger.warning(
                     "Unable to detect supported link types, as cache "
@@ -66,19 +62,19 @@ class CmdVersion(CmdBaseNoRepo):
                     "check.".format(relpath(repo.cache.local.cache_dir))
                 )
 
-            if psutil:
-                info += (
-                    "Filesystem type (cache directory): {fs_cache}\n"
-                ).format(fs_cache=self.get_fs_type(repo.cache.local.cache_dir))
         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:
-            info += ("Filesystem type (workspace): {fs_root}").format(
-                fs_root=self.get_fs_type(os.path.abspath(root_directory))
-            )
+            fs_root = self.get_fs_type(os.path.abspath(root_directory))
+            info.append(f"Filesystem type (workspace): {fs_root}")
 
-        logger.info(info)
+        logger.info("\n".join(info))
         return 0
 
     @staticmethod
@@ -98,9 +94,9 @@ class CmdVersion(CmdBaseNoRepo):
     @staticmethod
     def get_linktype_support_info(repo):
         links = {
-            "reflink": System.reflink,
-            "hardlink": System.hardlink,
-            "symlink": System.symlink,
+            "reflink": (System.reflink, None),
+            "hardlink": (System.hardlink, System.is_hardlink),
+            "symlink": (System.symlink, System.is_symlink),
         }
 
         fname = "." + str(uuid.uuid4())
@@ -110,26 +106,46 @@ class CmdVersion(CmdBaseNoRepo):
 
         cache = []
 
-        for name, link in links.items():
+        for name, (link, is_link) in links.items():
             try:
                 link(src, dst)
+                status = "supported"
+                if is_link and not is_link(dst):
+                    status = "broken"
                 os.unlink(dst)
-                supported = True
             except DvcException:
-                supported = False
-            cache.append(
-                "{name} - {supported}".format(
-                    name=name, supported=True if supported else False
-                )
-            )
+                status = "not supported"
+            cache.append(f"{name} - {status}")
         os.remove(src)
 
         return ", ".join(cache)
 
+    @staticmethod
+    def get_supported_remotes():
+        from dvc.remote import REMOTES
+
+        supported_remotes = []
+        for remote in REMOTES:
+            if not remote.get_missing_deps():
+                supported_remotes.append(remote.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/config.py

@@ -1,47 +1,41 @@
 """DVC config objects."""
-from __future__ import unicode_literals
-
-import copy
-import errno
 import logging
 import os
 import re
+from contextlib import contextmanager
+from functools import partial
+from urllib.parse import urlparse
 
 import configobj
-from voluptuous import Schema, Required, Optional, Invalid
-from voluptuous import All, Any, Lower, Range, Coerce, Match
+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
-from dvc.exceptions import NotDvcRepoError
-from dvc.utils.compat import open, str
+from dvc.exceptions import DvcException, NotDvcRepoError
+from dvc.path_info import PathInfo
+from dvc.utils import relpath
 
 logger = logging.getLogger(__name__)
 
 
 class ConfigError(DvcException):
-    """DVC config exception.
+    """DVC config exception."""
 
-    Args:
-        msg (str): error message.
-        cause (Exception): optional exception that has caused this error.
-    """
-
-    def __init__(self, msg, cause=None):
-        super(ConfigError, self).__init__(
-            "config file error: {}".format(msg), cause=cause
-        )
+    def __init__(self, msg):
+        super().__init__(f"config file error: {msg}")
 
 
 class NoRemoteError(ConfigError):
-    def __init__(self, command, cause=None):
-        msg = (
-            "no remote specified. Setup default remote with\n"
-            "    dvc config core.remote <name>\n"
-            "or use:\n"
-            "    dvc {} -r <name>\n".format(command)
-        )
-
-        super(NoRemoteError, self).__init__(msg, cause=cause)
+    pass
 
 
 def supported_cache_type(types):
@@ -65,13 +59,12 @@ def supported_cache_type(types):
 
 
 # Checks that value is either true or false and converts it to bool
-Bool = All(
+to_bool = Bool = All(
     Lower,
     Any("true", "false"),
     lambda v: v == "true",
     msg="expected true or false",
 )
-to_bool = Schema(Bool)
 
 
 def Choices(*choices):
@@ -84,8 +77,139 @@ def Choices(*choices):
     return Any(*choices, msg="expected one of {}".format(", ".join(choices)))
 
 
-class Config(object):  # pylint: disable=too-many-instance-attributes
-    """Class that manages configuration files for a dvc repo.
+def ByUrl(mapping):
+    schemas = walk_values(Schema, mapping)
+
+    def validate(data):
+        if "url" not in data:
+            raise Invalid("expected 'url'")
+
+        parsed = urlparse(data["url"])
+        # Windows absolute paths should really have scheme == "" (local)
+        if os.name == "nt" and len(parsed.scheme) == 1 and parsed.netloc == "":
+            return schemas[""](data)
+        if parsed.scheme not in schemas:
+            raise Invalid(f"Unsupported URL type {parsed.scheme}://")
+
+        return schemas[parsed.scheme](data)
+
+    return validate
+
+
+class RelPath(str):
+    pass
+
+
+REMOTE_COMMON = {
+    "url": str,
+    "checksum_jobs": All(Coerce(int), Range(1)),
+    Optional("no_traverse"): Bool,  # obsoleted
+    "verify": Bool,
+}
+LOCAL_COMMON = {
+    "type": supported_cache_type,
+    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,
+        "checksum_jobs": All(Coerce(int), Range(1)),
+        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,
+        "s3": str,
+        "gs": str,
+        "hdfs": str,
+        "ssh": str,
+        "azure": str,
+        # This is for default local cache
+        "dir": str,
+        **LOCAL_COMMON,
+    },
+    "remote": {
+        str: ByUrl(
+            {
+                "": {**LOCAL_COMMON, **REMOTE_COMMON},
+                "s3": {
+                    "region": str,
+                    "profile": str,
+                    "credentialpath": str,
+                    "endpointurl": str,
+                    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,
+                    "grant_write_acp": str,
+                    "grant_full_control": str,
+                    **REMOTE_COMMON,
+                },
+                "gs": {
+                    "projectname": str,
+                    "credentialpath": str,
+                    **REMOTE_COMMON,
+                },
+                "ssh": {
+                    "type": supported_cache_type,
+                    "port": Coerce(int),
+                    "user": str,
+                    "password": str,
+                    "ask_password": Bool,
+                    "keyfile": str,
+                    "timeout": Coerce(int),
+                    "gss_auth": Bool,
+                    **REMOTE_COMMON,
+                },
+                "hdfs": {"user": str, **REMOTE_COMMON},
+                "azure": {"connection_string": str, **REMOTE_COMMON},
+                "oss": {
+                    "oss_key_id": str,
+                    "oss_key_secret": str,
+                    "oss_endpoint": str,
+                    **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": {**HTTP_COMMON, **REMOTE_COMMON},
+                "https": {**HTTP_COMMON, **REMOTE_COMMON},
+                "remote": {str: object},  # Any of the above options are valid
+            }
+        )
+    },
+    "state": {
+        "row_limit": All(Coerce(int), Range(1)),
+        "row_cleanup_quota": All(Coerce(int), Range(0, 100)),
+    },
+}
+COMPILED_SCHEMA = Schema(SCHEMA)
+
+
+class Config(dict):
+    """Class that manages configuration files for a DVC repo.
 
     Args:
         dvc_dir (str): optional path to `.dvc` directory, that is used to
@@ -94,172 +218,21 @@ class Config(object):  # pylint: disable=too-many-instance-attributes
         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"
     APPAUTHOR = "iterative"
 
-    # NOTE: used internally in RemoteLOCAL to know config
-    # location, that url should resolved relative to.
-    PRIVATE_CWD = "_cwd"
+    # In the order they shadow each other
+    LEVELS = ("system", "global", "repo", "local")
 
     CONFIG = "config"
     CONFIG_LOCAL = "config.local"
 
-    CREDENTIALPATH = "credentialpath"
-
-    LEVEL_LOCAL = 0
-    LEVEL_REPO = 1
-    LEVEL_GLOBAL = 2
-    LEVEL_SYSTEM = 3
-
-    SECTION_CORE = "core"
-    SECTION_CORE_LOGLEVEL = "loglevel"
-    SECTION_CORE_LOGLEVEL_SCHEMA = All(
-        Lower, Choices("info", "debug", "warning", "error")
-    )
-    SECTION_CORE_REMOTE = "remote"
-    SECTION_CORE_INTERACTIVE = "interactive"
-    SECTION_CORE_ANALYTICS = "analytics"
-    SECTION_CORE_CHECKSUM_JOBS = "checksum_jobs"
-    SECTION_CORE_HARDLINK_LOCK = "hardlink_lock"
-
-    SECTION_CACHE = "cache"
-    SECTION_CACHE_DIR = "dir"
-    SECTION_CACHE_TYPE = "type"
-    SECTION_CACHE_PROTECTED = "protected"
-    SECTION_CACHE_SHARED = "shared"
-    SECTION_CACHE_SHARED_SCHEMA = All(Lower, Choices("group"))
-    SECTION_CACHE_LOCAL = "local"
-    SECTION_CACHE_S3 = "s3"
-    SECTION_CACHE_GS = "gs"
-    SECTION_CACHE_SSH = "ssh"
-    SECTION_CACHE_HDFS = "hdfs"
-    SECTION_CACHE_AZURE = "azure"
-    SECTION_CACHE_SLOW_LINK_WARNING = "slow_link_warning"
-    SECTION_CACHE_SCHEMA = {
-        SECTION_CACHE_LOCAL: str,
-        SECTION_CACHE_S3: str,
-        SECTION_CACHE_GS: str,
-        SECTION_CACHE_HDFS: str,
-        SECTION_CACHE_SSH: str,
-        SECTION_CACHE_AZURE: str,
-        SECTION_CACHE_DIR: str,
-        SECTION_CACHE_TYPE: supported_cache_type,
-        Optional(SECTION_CACHE_PROTECTED, default=False): Bool,
-        SECTION_CACHE_SHARED: SECTION_CACHE_SHARED_SCHEMA,
-        PRIVATE_CWD: str,
-        Optional(SECTION_CACHE_SLOW_LINK_WARNING, default=True): Bool,
-    }
-
-    SECTION_CORE_SCHEMA = {
-        SECTION_CORE_LOGLEVEL: SECTION_CORE_LOGLEVEL_SCHEMA,
-        SECTION_CORE_REMOTE: Lower,
-        Optional(SECTION_CORE_INTERACTIVE, default=False): Bool,
-        Optional(SECTION_CORE_ANALYTICS, default=True): Bool,
-        SECTION_CORE_CHECKSUM_JOBS: All(Coerce(int), Range(1)),
-        Optional(SECTION_CORE_HARDLINK_LOCK, default=False): Bool,
-    }
-
-    # aws specific options
-    SECTION_AWS_CREDENTIALPATH = CREDENTIALPATH
-    SECTION_AWS_ENDPOINT_URL = "endpointurl"
-    SECTION_AWS_LIST_OBJECTS = "listobjects"
-    SECTION_AWS_REGION = "region"
-    SECTION_AWS_PROFILE = "profile"
-    SECTION_AWS_USE_SSL = "use_ssl"
-    SECTION_AWS_SSE = "sse"
-    SECTION_AWS_ACL = "acl"
-    SECTION_AWS_GRANT_READ = "grant_read"
-    SECTION_AWS_GRANT_READ_ACP = "grant_read_acp"
-    SECTION_AWS_GRANT_WRITE_ACP = "grant_write_acp"
-    SECTION_AWS_GRANT_FULL_CONTROL = "grant_full_control"
-
-    # gcp specific options
-    SECTION_GCP_CREDENTIALPATH = CREDENTIALPATH
-    SECTION_GCP_PROJECTNAME = "projectname"
-
-    # azure specific option
-    SECTION_AZURE_CONNECTION_STRING = "connection_string"
-
-    # Alibabacloud oss options
-    SECTION_OSS_ACCESS_KEY_ID = "oss_key_id"
-    SECTION_OSS_ACCESS_KEY_SECRET = "oss_key_secret"
-    SECTION_OSS_ENDPOINT = "oss_endpoint"
-
-    # GDrive options
-    SECTION_GDRIVE_CLIENT_ID = "gdrive_client_id"
-    SECTION_GDRIVE_CLIENT_SECRET = "gdrive_client_secret"
-    SECTION_GDRIVE_USER_CREDENTIALS_FILE = "gdrive_user_credentials_file"
-
-    SECTION_REMOTE_REGEX = r'^\s*remote\s*"(?P<name>.*)"\s*$'
-    SECTION_REMOTE_FMT = 'remote "{}"'
-    SECTION_REMOTE_URL = "url"
-    SECTION_REMOTE_USER = "user"
-    SECTION_REMOTE_PORT = "port"
-    SECTION_REMOTE_KEY_FILE = "keyfile"
-    SECTION_REMOTE_TIMEOUT = "timeout"
-    SECTION_REMOTE_PASSWORD = "password"
-    SECTION_REMOTE_ASK_PASSWORD = "ask_password"
-    SECTION_REMOTE_GSS_AUTH = "gss_auth"
-    SECTION_REMOTE_NO_TRAVERSE = "no_traverse"
-    SECTION_REMOTE_SCHEMA = {
-        Required(SECTION_REMOTE_URL): str,
-        SECTION_AWS_REGION: str,
-        SECTION_AWS_PROFILE: str,
-        SECTION_AWS_CREDENTIALPATH: str,
-        SECTION_AWS_ENDPOINT_URL: str,
-        Optional(SECTION_AWS_LIST_OBJECTS, default=False): Bool,
-        Optional(SECTION_AWS_USE_SSL, default=True): Bool,
-        SECTION_AWS_SSE: str,
-        SECTION_AWS_ACL: str,
-        SECTION_AWS_GRANT_READ: str,
-        SECTION_AWS_GRANT_READ_ACP: str,
-        SECTION_AWS_GRANT_WRITE_ACP: str,
-        SECTION_AWS_GRANT_FULL_CONTROL: str,
-        SECTION_GCP_PROJECTNAME: str,
-        SECTION_CACHE_TYPE: supported_cache_type,
-        Optional(SECTION_CACHE_PROTECTED, default=False): Bool,
-        SECTION_REMOTE_USER: str,
-        SECTION_REMOTE_PORT: Coerce(int),
-        SECTION_REMOTE_KEY_FILE: str,
-        SECTION_REMOTE_TIMEOUT: Coerce(int),
-        SECTION_REMOTE_PASSWORD: str,
-        SECTION_REMOTE_ASK_PASSWORD: Bool,
-        SECTION_REMOTE_GSS_AUTH: Bool,
-        SECTION_AZURE_CONNECTION_STRING: str,
-        SECTION_OSS_ACCESS_KEY_ID: str,
-        SECTION_OSS_ACCESS_KEY_SECRET: str,
-        SECTION_OSS_ENDPOINT: str,
-        SECTION_GDRIVE_CLIENT_ID: str,
-        SECTION_GDRIVE_CLIENT_SECRET: str,
-        SECTION_GDRIVE_USER_CREDENTIALS_FILE: str,
-        PRIVATE_CWD: str,
-        Optional(SECTION_REMOTE_NO_TRAVERSE, default=True): Bool,
-    }
-
-    SECTION_STATE = "state"
-    SECTION_STATE_ROW_LIMIT = "row_limit"
-    SECTION_STATE_ROW_CLEANUP_QUOTA = "row_cleanup_quota"
-    SECTION_STATE_SCHEMA = {
-        SECTION_STATE_ROW_LIMIT: All(Coerce(int), Range(1)),
-        SECTION_STATE_ROW_CLEANUP_QUOTA: All(Coerce(int), Range(0, 100)),
-    }
-
-    SCHEMA = {
-        Optional(SECTION_CORE, default={}): SECTION_CORE_SCHEMA,
-        Match(SECTION_REMOTE_REGEX): SECTION_REMOTE_SCHEMA,
-        Optional(SECTION_CACHE, default={}): SECTION_CACHE_SCHEMA,
-        Optional(SECTION_STATE, default={}): SECTION_STATE_SCHEMA,
-    }
-    COMPILED_SCHEMA = Schema(SCHEMA)
-
     def __init__(self, dvc_dir=None, validate=True):
         self.dvc_dir = dvc_dir
-        self.validate = validate
 
         if not dvc_dir:
             try:
@@ -271,33 +244,31 @@ class Config(object):  # pylint: disable=too-many-instance-attributes
         else:
             self.dvc_dir = os.path.abspath(os.path.realpath(dvc_dir))
 
-        self.load()
+        self.load(validate=validate)
 
-    @staticmethod
-    def get_global_config_dir():
-        """Returns global config location. E.g. ~/.config/dvc/config.
+    @classmethod
+    def get_dir(cls, level):
+        from appdirs import user_config_dir, site_config_dir
 
-        Returns:
-            str: path to the global config directory.
-        """
-        from appdirs import user_config_dir
+        assert level in ("global", "system")
 
-        return user_config_dir(
-            appname=Config.APPNAME, appauthor=Config.APPAUTHOR
-        )
+        if level == "global":
+            return user_config_dir(cls.APPNAME, cls.APPAUTHOR)
+        if level == "system":
+            return site_config_dir(cls.APPNAME, cls.APPAUTHOR)
 
-    @staticmethod
-    def get_system_config_dir():
-        """Returns system config location. E.g. /etc/dvc.conf.
+    @cached_property
+    def files(self):
+        files = {
+            level: os.path.join(self.get_dir(level), self.CONFIG)
+            for level in ("system", "global")
+        }
 
-        Returns:
-            str: path to the system config directory.
-        """
-        from appdirs import site_config_dir
+        if self.dvc_dir is not None:
+            files["repo"] = os.path.join(self.dvc_dir, self.CONFIG)
+            files["local"] = os.path.join(self.dvc_dir, self.CONFIG_LOCAL)
 
-        return site_config_dir(
-            appname=Config.APPNAME, appauthor=Config.APPAUTHOR
-        )
+        return files
 
     @staticmethod
     def init(dvc_dir):
@@ -313,243 +284,156 @@ class Config(object):  # pylint: disable=too-many-instance-attributes
         open(config_file, "w+").close()
         return Config(dvc_dir)
 
-    def _resolve_cache_path(self, config):
-        cache = config.get(self.SECTION_CACHE)
-        if cache is None:
-            return
-
-        cache_dir = cache.get(self.SECTION_CACHE_DIR)
-        if cache_dir is None:
-            return
-
-        cache[self.PRIVATE_CWD] = os.path.dirname(config.filename)
-
-    def _resolve_paths(self, config):
-        if config.filename is None:
-            return config
-
-        ret = copy.deepcopy(config)
-        self._resolve_cache_path(ret)
-
-        for section in ret.values():
-            if self.SECTION_REMOTE_URL not in section.keys():
-                continue
-
-            section[self.PRIVATE_CWD] = os.path.dirname(ret.filename)
-
-        return ret
-
-    def _load_configs(self):
-        system_config_file = os.path.join(
-            self.get_system_config_dir(), self.CONFIG
-        )
-
-        global_config_file = os.path.join(
-            self.get_global_config_dir(), self.CONFIG
-        )
-
-        self._system_config = configobj.ConfigObj(system_config_file)
-        self._global_config = configobj.ConfigObj(global_config_file)
-        self._repo_config = configobj.ConfigObj()
-        self._local_config = configobj.ConfigObj()
-
-        if not self.dvc_dir:
-            return
-
-        config_file = os.path.join(self.dvc_dir, self.CONFIG)
-        config_local_file = os.path.join(self.dvc_dir, self.CONFIG_LOCAL)
-
-        self._repo_config = configobj.ConfigObj(config_file)
-        self._local_config = configobj.ConfigObj(config_local_file)
-
-    @property
-    def config_local_file(self):
-        return self._local_config.filename
-
-    @property
-    def config_file(self):
-        return self._repo_config.filename
-
-    def load(self):
+    def load(self, validate=True):
         """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.
         """
-        self._load_configs()
+        conf = self.load_config_to_level()
 
-        self.config = configobj.ConfigObj()
-        for c in [
-            self._system_config,
-            self._global_config,
-            self._repo_config,
-            self._local_config,
-        ]:
-            c = self._resolve_paths(c)
-            c = self._lower(c)
-            self.config.merge(c)
+        if validate:
+            conf = self.validate(conf)
 
-        if not self.validate:
-            return
+        self.clear()
+        self.update(conf)
 
-        d = self.config.dict()
-        try:
-            d = self.COMPILED_SCHEMA(d)
-        except Invalid as exc:
-            raise ConfigError(str(exc), cause=exc)
-        self.config = configobj.ConfigObj(d, write_empty_values=True)
+        # Add resolved default cache.dir
+        if not self["cache"].get("dir") and self.dvc_dir:
+            self["cache"]["dir"] = os.path.join(self.dvc_dir, "cache")
 
-    def save(self, config=None):
-        """Saves config to config files.
+    def load_one(self, level):
+        conf = _load_config(self.files[level])
+        conf = self._load_paths(conf, self.files[level])
 
-        Raises:
-            dvc.config.ConfigError: thrown if failed to write config file.
-        """
-        if config is not None:
-            clist = [config]
-        else:
-            clist = [
-                self._system_config,
-                self._global_config,
-                self._repo_config,
-                self._local_config,
-            ]
+        # Auto-verify sections
+        for key in COMPILED_SCHEMA.schema:
+            conf.setdefault(key, {})
 
-        for conf in clist:
-            self._save(conf)
+        return conf
 
+    @staticmethod
+    def _load_paths(conf, filename):
+        abs_conf_dir = os.path.abspath(os.path.dirname(filename))
+
+        def resolve(path):
+            if os.path.isabs(path) or re.match(r"\w+://", path):
+                return path
+            return RelPath(os.path.join(abs_conf_dir, path))
+
+        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)
+        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, "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")
+
+        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()
 
     @staticmethod
-    def _save(config):
-        if config.filename is None:
-            return
-
-        logger.debug("Writing '{}'.".format(config.filename))
-        dname = os.path.dirname(os.path.abspath(config.filename))
+    def validate(data):
         try:
-            os.makedirs(dname)
-        except OSError as exc:
-            if exc.errno != errno.EEXIST:
-                raise
-        config.write()
+            return COMPILED_SCHEMA(data)
+        except Invalid as exc:
+            raise ConfigError(str(exc)) from None
 
-    def unset(self, section, opt=None, level=None, force=False):
-        """Unsets specified option and/or section in the config.
 
-        Args:
-            section (str): section name.
-            opt (str): optional option name.
-            level (int): config level to use.
-            force (bool): don't error-out even if section doesn't exist. False
-                by default.
+def _load_config(filename):
+    conf_obj = configobj.ConfigObj(filename)
+    return _parse_remotes(_lower_keys(conf_obj.dict()))
 
-        Raises:
-            dvc.config.ConfigError: thrown if section doesn't exist and
-                `force != True`.
-        """
-        config = self.get_configobj(level)
 
-        if section not in config.keys():
-            if force:
-                return
-            raise ConfigError("section '{}' doesn't exist".format(section))
+def _save_config(filename, conf_dict):
+    logger.debug(f"Writing '{filename}'.")
+    os.makedirs(os.path.dirname(filename), exist_ok=True)
 
-        if opt:
-            if opt not in config[section].keys():
-                if force:
-                    return
-                raise ConfigError(
-                    "option '{}.{}' doesn't exist".format(section, opt)
-                )
-            del config[section][opt]
+    config = configobj.ConfigObj(_pack_remotes(conf_dict))
+    config.filename = filename
+    config.write()
 
-            if not config[section]:
-                del config[section]
+
+def _parse_remotes(conf):
+    result = {"remote": {}}
+
+    for section, val in conf.items():
+        name = re_find(r'^\s*remote\s*"(.*)"\s*$', section)
+        if name:
+            result["remote"][name] = val
         else:
-            del config[section]
+            result[section] = val
 
-        self.save(config)
+    return result
 
-    def set(self, section, opt, value, level=None, force=True):
-        """Sets specified option in the config.
 
-        Args:
-            section (str): section name.
-            opt (str): option name.
-            value: value to set option to.
-            level (int): config level to use.
-            force (bool): set option even if section already exists. True by
-                default.
+def _pack_remotes(conf):
+    # Drop empty sections
+    result = compact(conf)
 
-        Raises:
-            dvc.config.ConfigError: thrown if section already exists and
-                `force != True`.
+    # Transform remote.name -> 'remote "name"'
+    for name, val in conf["remote"].items():
+        result[f'remote "{name}"'] = val
+    result.pop("remote", None)
 
-        """
-        config = self.get_configobj(level)
+    return result
 
-        if section not in config.keys():
-            config[section] = {}
-        elif not force:
-            raise ConfigError(
-                "Section '{}' already exists. Use `-f|--force` to overwrite "
-                "section with new value.".format(section)
-            )
 
-        config[section][opt] = value
-        self.save(config)
+def _merge(into, update):
+    """Merges second dict into first recursively"""
+    for key, val in update.items():
+        if isinstance(into.get(key), dict) and isinstance(val, dict):
+            _merge(into[key], val)
+        else:
+            into[key] = val
 
-    def get(self, section, opt=None, level=None):
-        """Return option value from the config.
 
-        Args:
-            section (str): section name.
-            opt (str): option name.
-            level (int): config level to use.
-
-        Returns:
-            value (str, int): option value.
-        """
-        config = self.get_configobj(level)
-
-        if section not in config.keys():
-            raise ConfigError("section '{}' doesn't exist".format(section))
-
-        if opt not in config[section].keys():
-            raise ConfigError(
-                "option '{}.{}' doesn't exist".format(section, opt)
-            )
-
-        return config[section][opt]
-
-    @staticmethod
-    def _lower(config):
-        new_config = configobj.ConfigObj()
-        for s_key, s_value in config.items():
-            new_s = {}
-            for key, value in s_value.items():
-                new_s[key.lower()] = str(value)
-            new_config[s_key.lower()] = new_s
-        return new_config
-
-    def get_configobj(self, level):
-        configs = {
-            self.LEVEL_LOCAL: self._local_config,
-            self.LEVEL_REPO: self._repo_config,
-            self.LEVEL_GLOBAL: self._global_config,
-            self.LEVEL_SYSTEM: self._system_config,
-        }
-
-        return configs.get(level, self._repo_config)
-
-    def list_options(self, section_regex, option, level=None):
-        ret = {}
-        config = self.get_configobj(level)
-        for section in config.keys():
-            r = re.match(section_regex, section)
-            if r:
-                name = r.group("name")
-                value = config[section].get(option, "")
-                ret[name] = value
-        return ret
+def _lower_keys(data):
+    return {
+        k.lower(): _lower_keys(v) if isinstance(v, dict) else v
+        for k, v in data.items()
+    }

dvc/daemon.py

@@ -1,5 +1,4 @@
 """Launch `dvc daemon` command in a separate detached process."""
-from __future__ import unicode_literals
 
 import inspect
 import logging
@@ -8,10 +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.compat import cast_bytes_py2
-
+from dvc.utils import fix_env, is_binary
 
 logger = logging.getLogger(__name__)
 
@@ -70,7 +66,7 @@ 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)
@@ -79,7 +75,7 @@ def _spawn(cmd, env):
     else:
         raise NotImplementedError
 
-    logger.debug("Spawned '{}'".format(cmd))
+    logger.debug(f"Spawned '{cmd}'")
 
 
 def daemon(args):
@@ -99,9 +95,7 @@ def daemon(args):
 
     env = fix_env()
     file_path = os.path.abspath(inspect.stack()[0][1])
-    env[cast_bytes_py2("PYTHONPATH")] = cast_bytes_py2(
-        os.path.dirname(os.path.dirname(file_path))
-    )
-    env[cast_bytes_py2(DVC_DAEMON)] = cast_bytes_py2("1")
+    env["PYTHONPATH"] = os.path.dirname(os.path.dirname(file_path))
+    env[DVC_DAEMON] = "1"
 
     _spawn(cmd, env)

dvc/dagascii.py

@@ -1,6 +1,4 @@
 """Draws DAG in ASCII."""
-from __future__ import print_function
-from __future__ import unicode_literals
 
 import logging
 import math
@@ -8,15 +6,12 @@ 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
 
 logger = logging.getLogger(__name__)
 
@@ -42,17 +37,19 @@ 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(
         "Unable to find `less` in the PATH. Check out "
-        "man.dvc.org/doc/command-reference/pipeline/show for more info."
+        "{} for more info.".format(
+            format_link("https://man.dvc.org/pipeline/show")
+        )
     )
     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:
@@ -95,7 +92,7 @@ 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."""
@@ -148,21 +145,21 @@ 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 +213,7 @@ 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()

dvc/data_cloud.py

@@ -1,17 +1,14 @@
 """Manages dvc remotes that user can use with push/pull/status commands."""
-from __future__ import unicode_literals
 
 import logging
 
-from dvc.config import Config
 from dvc.config import NoRemoteError
 from dvc.remote import Remote
 
-
 logger = logging.getLogger(__name__)
 
 
-class DataCloud(object):
+class DataCloud:
     """Class that manages dvc remotes.
 
     Args:
@@ -25,69 +22,91 @@ class DataCloud(object):
     def __init__(self, repo):
         self.repo = repo
 
-    @property
-    def _config(self):
-        return self.repo.config.config
+    def get_remote(self, name=None, command="<command>"):
+        if not name:
+            name = self.repo.config["core"].get("remote")
 
-    @property
-    def _core(self):
-        return self._config.get(Config.SECTION_CORE, {})
+        if name:
+            return self._init_remote(name)
 
-    def get_remote(self, remote=None, command="<command>"):
-        if not remote:
-            remote = self._core.get(Config.SECTION_CORE_REMOTE)
+        if bool(self.repo.config["remote"]):
+            error_msg = (
+                "no remote specified. Setup default remote with\n"
+                "    dvc remote default <remote name>\n"
+                "or use:\n"
+                "    dvc {} -r <remote name>".format(command)
+            )
+        else:
+            error_msg = (
+                "no remote specified. Create a default remote with\n"
+                "    dvc remote add -d <remote name> <remote url>"
+            )
 
-        if remote:
-            return self._init_remote(remote)
+        raise NoRemoteError(error_msg)
 
-        raise NoRemoteError(command)
+    def _init_remote(self, name):
+        return Remote(self.repo, name=name)
 
-    def _init_remote(self, remote):
-        return Remote(self.repo, name=remote)
-
-    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.
         """
-        return self.repo.cache.local.pull(
-            cache,
-            jobs=jobs,
-            remote=self.get_remote(remote, "pull"),
-            show_checksums=show_checksums,
+        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:
+            self._save_pulled_checksums(cache)
+
+        return downloaded_items_num
+
+    def _save_pulled_checksums(self, cache):
+        for checksum in cache.scheme_keys("local"):
+            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()`)
+                self.repo.state.save(cache_file, checksum)
+
     def status(self, cache, jobs=None, remote=None, show_checksums=False):
         """Check status of data items in a cloud-agnostic way.
 
         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 +1,39 @@
-from __future__ import unicode_literals
+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.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 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
+    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.GS: GSDependency,
+    Schemes.HDFS: HDFSDependency,
+    Schemes.HTTP: HTTPDependency,
+    Schemes.HTTPS: HTTPSDependency,
 }
 
 
@@ -40,34 +42,36 @@ 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):
-    from dvc.utils.compat import urlparse
-
-    parsed = urlparse(p)
-
-    if parsed.scheme == "remote":
+    parsed = urlparse(p) if p else None
+    if parsed and parsed.scheme == "remote":
         remote = 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
 
@@ -75,6 +79,31 @@ def loadd_from(stage, d_list):
 def loads_from(stage, s_list, erepo=None):
     ret = []
     for s in s_list:
-        info = {DependencyREPO.PARAM_REPO: erepo} if erepo else {}
+        info = {RepoDependency.PARAM_REPO: erepo} if erepo else {}
         ret.append(_get(stage, s, info))
     return ret
+
+
+def _parse_params(path_params):
+    path, _, params_str = path_params.rpartition(":")
+    params = params_str.split(",")
+    return path, params
+
+
+def loads_params(stage, s_list):
+    # Creates an object for each unique file that is referenced in the list
+    params_by_path = defaultdict(list)
+    for s in s_list:
+        path, params = _parse_params(s)
+        params_by_path[path].extend(params)
+
+    d_list = []
+    for path, params in params_by_path.items():
+        d_list.append(
+            {
+                BaseOutput.PARAM_PATH: path,
+                ParamsDependency.PARAM_PARAMS: params,
+            }
+        )
+
+    return loadd_from(stage, d_list)

dvc/dependency/base.py

@@ -1,33 +1,29 @@
-from __future__ import unicode_literals
-
 from dvc.exceptions import DvcException
 
 
 class DependencyDoesNotExistError(DvcException):
     def __init__(self, path):
-        msg = "dependency '{}' does not exist".format(path)
-        super(DependencyDoesNotExistError, self).__init__(msg)
+        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)
-        super(DependencyIsNotFileOrDirError, self).__init__(msg)
+        msg = f"dependency '{path}' is not a file or directory"
+        super().__init__(msg)
 
 
 class DependencyIsStageFileError(DvcException):
     def __init__(self, path):
-        super(DependencyIsStageFileError, self).__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
     IsNotFileOrDirError = DependencyIsNotFileOrDirError
     IsStageFileError = DependencyIsStageFileError
 
-    def update(self):
+    def update(self, rev=None):
         pass

dvc/dependency/gs.py

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-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

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-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

@@ -1,9 +1,7 @@
-from __future__ import unicode_literals
-
-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 HTTPRemote
 
 
-class DependencyHTTP(DependencyBase, OutputBase):
-    REMOTE = RemoteHTTP
+class HTTPDependency(BaseDependency, BaseOutput):
+    REMOTE = HTTPRemote

dvc/dependency/https.py

@@ -1,8 +1,7 @@
-from __future__ import unicode_literals
+from dvc.remote.https import HTTPSRemote
 
-from .http import DependencyHTTP
-from dvc.remote.https import RemoteHTTPS
+from .http import HTTPDependency
 
 
-class DependencyHTTPS(DependencyHTTP):
-    REMOTE = RemoteHTTPS
+class HTTPSDependency(HTTPDependency):
+    REMOTE = HTTPSRemote

dvc/dependency/local.py

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-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 _dyn_load(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

@@ -1,31 +1,30 @@
-from __future__ import unicode_literals
-
-import copy
 import os
-from contextlib import contextmanager
-from dvc.utils.compat import FileNotFoundError
 
-from funcy import merge
+from voluptuous import Required
 
-from .local import DependencyLOCAL
-from dvc.external_repo import external_repo
-from dvc.utils.compat import str
 from dvc.exceptions import OutputNotFoundError
-from dvc.exceptions import PathMissingError
-from dvc.utils.fs import fs_copy
+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 = {PARAM_URL: str, PARAM_REV: str, PARAM_REV_LOCK: str}
+    REPO_SCHEMA = {
+        PARAM_REPO: {
+            Required(PARAM_URL): str,
+            PARAM_REV: str,
+            PARAM_REV_LOCK: str,
+        }
+    }
 
     def __init__(self, def_repo, stage, *args, **kwargs):
         self.def_repo = def_repo
-        super(DependencyREPO, self).__init__(stage, *args, **kwargs)
+        super().__init__(stage, *args, **kwargs)
 
     def _parse_path(self, remote, path):
         return None
@@ -37,24 +36,33 @@ class DependencyREPO(DependencyLOCAL):
     @property
     def repo_pair(self):
         d = self.def_repo
-        return d[self.PARAM_URL], d[self.PARAM_REV_LOCK] or d[self.PARAM_REV]
+        rev = d.get(self.PARAM_REV_LOCK) or d.get(self.PARAM_REV)
+        return d[self.PARAM_URL], rev
 
     def __str__(self):
         return "{} ({})".format(self.def_path, self.def_repo[self.PARAM_URL])
 
-    @contextmanager
-    def _make_repo(self, **overrides):
-        with external_repo(**merge(self.def_repo, overrides)) as repo:
-            yield repo
+    def _make_repo(self, *, locked=True):
+        from dvc.external_repo import external_repo
+
+        d = self.def_repo
+        rev = (d.get("rev_lock") if locked else None) or d.get("rev")
+        return external_repo(d["url"], rev=rev)
+
+    def _get_checksum(self, locked=True):
+        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 are polluting our repo cache with some dir listing here
+                return self.repo.cache.local.get_checksum(path)
 
     def status(self):
-        with self._make_repo() as repo:
-            current = repo.find_out_by_relpath(self.def_path).info
+        current_checksum = self._get_checksum(locked=True)
+        updated_checksum = self._get_checksum(locked=False)
 
-        with self._make_repo(rev_lock=None) as repo:
-            updated = repo.find_out_by_relpath(self.def_path).info
-
-        if current != updated:
+        if current_checksum != updated_checksum:
             return {str(self): "update available"}
 
         return {}
@@ -65,55 +73,19 @@ class DependencyREPO(DependencyLOCAL):
     def dumpd(self):
         return {self.PARAM_PATH: self.def_path, self.PARAM_REPO: self.def_repo}
 
-    def fetch(self):
-        with self._make_repo(
-            cache_dir=self.repo.cache.local.cache_dir
-        ) as repo:
-            self.def_repo[self.PARAM_REV_LOCK] = repo.scm.get_rev()
-
-            out = repo.find_out_by_relpath(self.def_path)
-            with repo.state:
-                repo.cloud.pull(out.get_used_cache())
-
-        return out
-
-    @staticmethod
-    def _is_git_file(repo, path):
-        if not os.path.isabs(path):
-            try:
-                output = repo.find_out_by_relpath(path)
-                if not output.use_cache:
-                    return True
-            except OutputNotFoundError:
-                return True
-        return False
-
-    def _copy_if_git_file(self, to_path):
-        src_path = self.def_path
-        with self._make_repo(
-            cache_dir=self.repo.cache.local.cache_dir
-        ) as repo:
-            if not self._is_git_file(repo, src_path):
-                return False
-
-            src_full_path = os.path.join(repo.root_dir, src_path)
-            dst_full_path = os.path.abspath(to_path)
-            fs_copy(src_full_path, dst_full_path)
-        return True
-
     def download(self, to):
-        try:
-            if self._copy_if_git_file(to.fspath):
-                return
+        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()
 
-            out = self.fetch()
-            to.info = copy.copy(out.info)
-            to.checkout()
-        except (FileNotFoundError):
-            raise PathMissingError(
-                self.def_path, self.def_repo[self.PARAM_URL]
-            )
+            if hasattr(repo, "cache"):
+                repo.cache.local.cache_dir = self.repo.cache.local.cache_dir
 
-    def update(self):
-        with self._make_repo(rev_lock=None) as repo:
+            repo.pull_to(self.def_path, to.path_info)
+
+    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()

dvc/dependency/s3.py

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-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

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-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 +1,270 @@
+import contextlib
+import logging
+import os
+
+from voluptuous import MultipleInvalid
+
+import dvc.prompt as prompt
+from dvc import serialize
+from dvc.exceptions import DvcException
+from dvc.stage.exceptions import (
+    StageFileAlreadyExistsError,
+    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.stage import (
+    dump_stage_file,
+    parse_stage,
+    parse_stage_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_stage(stage_text, self.path)
+        self.validate(d, self.relpath)
+        return d, stage_text
+
+    @classmethod
+    def validate(cls, d, fname=None):
+        assert cls.SCHEMA
+        try:
+            cls.SCHEMA(d)
+        except MultipleInvalid as exc:
+            raise StageFileFormatError(f"'{fname}' format error: {exc}")
+
+    def remove_with_prompt(self, force=False):
+        raise NotImplementedError
+
+    def remove(self, force=False):
+        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
+
+    def __init__(self, repo, path):
+        super().__init__(repo, path)
+
+    @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_stage_file(self.path, serialize.to_single_stage_file(stage))
+        self.repo.scm.track_file(relpath(self.path))
+
+    def remove_with_prompt(self, force=False):
+        if not self.exists():
+            return
+
+        msg = (
+            "'{}' already exists. Do you wish to run the command and "
+            "overwrite it?".format(relpath(self.path))
+        )
+        if not (force or prompt.confirm(msg)):
+            raise StageFileAlreadyExistsError(self.path)
+
+        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, **kwargs):
+        """Dumps given stage appropriately in the dvcfile."""
+        from dvc.stage import PipelineStage
+
+        assert isinstance(stage, PipelineStage)
+        check_dvc_filename(self.path)
+        self._dump_lockfile(stage)
+        if update_pipeline and not stage.is_data_source:
+            self._dump_pipeline_file(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_stage_for_update(fd.read(), self.path)
+        else:
+            open(self.path, "w+").close()
+
+        data["stages"] = data.get("stages", {})
+        stage_data = serialize.to_pipeline_file(stage)
+        if data["stages"].get(stage.name):
+            orig_stage_data = data["stages"][stage.name]
+            apply_diff(stage_data[stage.name], orig_stage_data)
+        else:
+            data["stages"].update(stage_data)
+
+        dump_stage_file(self.path, data)
+        self.repo.scm.track_file(relpath(self.path))
+
+    @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()
+
+
+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_stage(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():
+            data = stage_data
+            open(self.path, "w+").close()
+        else:
+            with self.repo.tree.open(self.path, "r") as fd:
+                data = parse_stage_for_update(fd.read(), self.path)
+            data.update(stage_data)
+
+        dump_stage_file(self.path, data)
+        self.repo.scm.track_file(relpath(self.path))
+
+
+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

@@ -1,32 +1,19 @@
 """Exceptions raised by the dvc."""
-from __future__ import unicode_literals
+from funcy import first
 
-import traceback
-
-from dvc.utils import relpath
-from dvc.utils.compat import builtin_str
-from dvc.utils.compat import str
+from dvc.utils import format_link, relpath
 
 
 class DvcException(Exception):
-    """Base class for all dvc exceptions.
+    """Base class for all dvc exceptions."""
 
-    Args:
-        msg (unicode): message for this exception.
-        cause (Exception): optional cause exception.
-    """
+    def __init__(self, msg, *args):
+        assert msg
+        super().__init__(msg, *args)
 
-    def __init__(self, msg, cause=None):
-        # NOTE: unlike python 3, python 2 doesn't have built-in support
-        # for chained exceptions, so we are using our own implementation.
-        self.cause = cause
-        self.cause_tb = None
-        if cause:
-            try:
-                self.cause_tb = traceback.format_exc()
-            except AttributeError:  # pragma: no cover
-                pass
-        super(DvcException, self).__init__(msg)
+
+class InvalidArgumentError(ValueError, DvcException):
+    """Thrown if arguments are invalid."""
 
 
 class OutputDuplicationError(DvcException):
@@ -39,18 +26,19 @@ class OutputDuplicationError(DvcException):
     """
 
     def __init__(self, output, stages):
-        assert isinstance(output, str) or isinstance(output, builtin_str)
-        assert isinstance(stages, list)
-        assert all(
-            isinstance(stage, str) or isinstance(stage, builtin_str)
-            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(stages))
-        super(OutputDuplicationError, self).__init__(msg)
+        assert isinstance(output, str)
+        assert all(hasattr(stage, "relpath") for stage 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):
@@ -63,8 +51,8 @@ class OutputNotFoundError(DvcException):
     def __init__(self, output, repo=None):
         self.output = output
         self.repo = repo
-        super(OutputNotFoundError, self).__init__(
-            "unable to find DVC-file with output '{path}'".format(
+        super().__init__(
+            "Unable to find DVC-file with output '{path}'".format(
                 path=relpath(self.output)
             )
         )
@@ -75,21 +63,17 @@ class StagePathAsOutputError(DvcException):
     an output of another stage.
 
     Args:
-        cwd (str): path to the directory.
-        fname (str): path to the DVC-file that has cwd specified as an
-            output.
+        stage (Stage): a stage that is in some other stages output
+        output (str): an output covering the stage above
     """
 
-    def __init__(self, wdir, fname):
-        assert isinstance(wdir, str) or isinstance(wdir, builtin_str)
-        assert isinstance(fname, str) or isinstance(fname, builtin_str)
-        msg = (
-            "current working directory '{cwd}' is specified as an output in "
-            "'{fname}'. Use another CWD to prevent any data removal.".format(
-                cwd=wdir, fname=fname
+    def __init__(self, stage, output):
+        assert isinstance(output, str)
+        super().__init__(
+            "{stage} is within an output '{output}' of another stage".format(
+                stage=stage, output=output
             )
         )
-        super(StagePathAsOutputError, self).__init__(msg)
 
 
 class CircularDependencyError(DvcException):
@@ -101,13 +85,10 @@ class CircularDependencyError(DvcException):
     """
 
     def __init__(self, dependency):
-        assert isinstance(dependency, (str, builtin_str))
+        assert isinstance(dependency, str)
 
-        msg = (
-            "file/directory '{}' is specified as an output and as a "
-            "dependency."
-        )
-        super(CircularDependencyError, self).__init__(msg.format(dependency))
+        msg = "'{}' is specified as an output and as a dependency."
+        super().__init__(msg.format(dependency))
 
 
 class ArgumentDuplicationError(DvcException):
@@ -119,9 +100,8 @@ class ArgumentDuplicationError(DvcException):
     """
 
     def __init__(self, path):
-        assert isinstance(path, (str, builtin_str))
-        msg = "file '{}' is specified more than once."
-        super(ArgumentDuplicationError, self).__init__(msg.format(path))
+        assert isinstance(path, str)
+        super().__init__(f"file '{path}' is specified more than once.")
 
 
 class MoveNotDataSourceError(DvcException):
@@ -139,157 +119,122 @@ class MoveNotDataSourceError(DvcException):
             "it by hand, or remove '{path}' and create a new one at the "
             "desired location."
         )
-        super(MoveNotDataSourceError, self).__init__(msg.format(path=path))
+        super().__init__(msg.format(path=path))
 
 
 class NotDvcRepoError(DvcException):
-    """Thrown if a directory is not a dvc repo.
-
-    Args:
-        root (str): path to the directory.
-    """
-
-    def __init__(self, root):
-        msg = (
-            "you are not inside of a dvc repository "
-            "(checked up to mount point '{}')"
-        )
-        super(NotDvcRepoError, self).__init__(msg.format(root))
+    """Thrown if a directory is not a DVC repo"""
 
 
 class DvcParserError(DvcException):
     """Base class for CLI parser errors."""
 
     def __init__(self):
-        super(DvcParserError, self).__init__("parser error")
+        super().__init__("parser error")
 
 
 class CyclicGraphError(DvcException):
     def __init__(self, stages):
         assert isinstance(stages, list)
-        stages = "\n".join("\t- {}".format(stage) 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(CyclicGraphError, self).__init__(msg)
+        super().__init__(msg)
 
 
 class ConfirmRemoveError(DvcException):
     def __init__(self, path):
-        super(ConfirmRemoveError, self).__init__(
-            "unable to remove '{}' without a confirmation from the user. Use "
+        super().__init__(
+            "unable to remove '{}' without a confirmation. Use "
             "`-f` to force.".format(path)
         )
 
 
 class InitError(DvcException):
-    def __init__(self, msg):
-        super(InitError, self).__init__(msg)
+    pass
 
 
 class ReproductionError(DvcException):
-    def __init__(self, dvc_file_name, ex):
+    def __init__(self, dvc_file_name):
         self.path = dvc_file_name
-        msg = "failed to reproduce '{}'".format(dvc_file_name)
-        super(ReproductionError, self).__init__(msg, cause=ex)
+        super().__init__(f"failed to reproduce '{dvc_file_name}'")
 
 
 class BadMetricError(DvcException):
     def __init__(self, paths):
-        super(BadMetricError, self).__init__(
-            "the following metrics do not exists, "
+        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)
             )
         )
 
 
 class NoMetricsError(DvcException):
     def __init__(self):
-        super(NoMetricsError, self).__init__(
+        super().__init__(
             "no metric files in this repository. "
             "Use `dvc metrics add` to add a metric file to track."
         )
 
 
 class StageFileCorruptedError(DvcException):
-    def __init__(self, path, cause=None):
+    def __init__(self, path):
         path = relpath(path)
-        super(StageFileCorruptedError, self).__init__(
+        super().__init__(
             "unable to read DVC-file: {} "
-            "YAML file structure is corrupted".format(path),
-            cause=cause,
+            "YAML file structure is corrupted".format(path)
         )
 
 
 class RecursiveAddingWhileUsingFilename(DvcException):
     def __init__(self):
-        super(RecursiveAddingWhileUsingFilename, self).__init__(
+        super().__init__(
             "cannot use `fname` with multiple targets or `-R|--recursive`"
         )
 
 
 class OverlappingOutputPathsError(DvcException):
-    def __init__(self, out_1, out_2):
-        super(OverlappingOutputPathsError, self).__init__(
-            "Paths for outs:\n'{}'('{}')\n'{}'('{}')\noverlap. To avoid "
-            "unpredictable behaviour, rerun command with non overlapping outs "
-            "paths.".format(
-                str(out_1),
-                out_1.stage.relpath,
-                str(out_2),
-                out_2.stage.relpath,
-            )
-        )
+    def __init__(self, parent, overlapping_out, message):
+        self.parent = parent
+        self.overlapping_out = overlapping_out
+        super().__init__(message)
 
 
 class CheckoutErrorSuggestGit(DvcException):
-    def __init__(self, target, cause):
-        super(CheckoutErrorSuggestGit, self).__init__(
-            "Did you mean `git checkout {}`?".format(target), cause=cause
-        )
+    def __init__(self, target):
+        super().__init__(f"Did you mean `git checkout {target}`?")
 
 
 class ETagMismatchError(DvcException):
     def __init__(self, etag, cached_etag):
-        super(ETagMismatchError, self).__init__(
+        super().__init__(
             "ETag mismatch detected when copying file to cache! "
             "(expected: '{}', actual: '{}')".format(etag, cached_etag)
         )
 
 
 class FileMissingError(DvcException):
-    def __init__(self, path, cause=None):
-        super(FileMissingError, self).__init__(
-            "Can't find '{}' neither locally nor on remote".format(path),
-            cause=cause,
-        )
+    def __init__(self, path):
+        self.path = path
+        super().__init__(f"Can't find '{path}' neither locally nor on remote")
 
 
 class DvcIgnoreInCollectedDirError(DvcException):
     def __init__(self, ignore_dirname):
-        super(DvcIgnoreInCollectedDirError, self).__init__(
+        super().__init__(
             ".dvcignore file should not be in collected dir path: "
             "'{}'".format(ignore_dirname)
         )
 
 
-class UrlNotDvcRepoError(DvcException):
-    def __init__(self, url):
-        super(UrlNotDvcRepoError, self).__init__(
-            "URL '{}' is not a dvc repository.".format(url)
-        )
-
-
 class GitHookAlreadyExistsError(DvcException):
     def __init__(self, hook_name):
-        super(GitHookAlreadyExistsError, self).__init__(
-            "Hook '{}' already exists. Please refer to "
-            "https://man.dvc.org/install "
-            "for more info.".format(hook_name)
+        super().__init__(
+            "Hook '{}' already exists. Please refer to {} for more "
+            "info.".format(
+                hook_name, format_link("https://man.dvc.org/install")
+            )
         )
 
 
@@ -297,28 +242,26 @@ class DownloadError(DvcException):
     def __init__(self, amount):
         self.amount = amount
 
-        super(DownloadError, self).__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(UploadError, self).__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(CheckoutError, self).__init__(m)
+        super().__init__(m)
 
 
 class CollectCacheError(DvcException):
@@ -327,14 +270,14 @@ class CollectCacheError(DvcException):
 
 class NoRemoteInExternalRepoError(DvcException):
     def __init__(self, url):
-        super(NoRemoteInExternalRepoError, self).__init__(
-            "No DVC remote is specified in target repository '{}'.".format(url)
+        super().__init__(
+            f"No DVC remote is specified in target repository '{url}'."
         )
 
 
 class NoOutputInExternalRepoError(DvcException):
     def __init__(self, path, external_repo_path, external_repo_url):
-        super(NoOutputInExternalRepoError, self).__init__(
+        super().__init__(
             "Output '{}' not found in target repository '{}'".format(
                 relpath(path, external_repo_path), external_repo_url
             )
@@ -343,13 +286,43 @@ class NoOutputInExternalRepoError(DvcException):
 
 class HTTPError(DvcException):
     def __init__(self, code, reason):
-        super(HTTPError, self).__init__("'{} {}'".format(code, reason))
+        super().__init__(f"'{code} {reason}'")
 
 
 class PathMissingError(DvcException):
-    def __init__(self, path, repo):
+    default_msg = (
+        "The path '{}' does not exist in the target repository '{}'"
+        " neither as a DVC output nor as a Git-tracked file."
+    )
+    default_msg_output_only = (
+        "The path '{}' does not exist in the target repository '{}'"
+        " as an DVC output."
+    )
+
+    def __init__(self, path, repo, output_only=False):
         msg = (
-            "The path '{}' does not exist in the target repository '{}'"
-            " neighther as an output nor a git-handled file."
+            self.default_msg
+            if not output_only
+            else self.default_msg_output_only
         )
-        super(PathMissingError, self).__init__(msg.format(path, repo))
+        super().__init__(msg.format(path, repo))
+        self.output_only = output_only
+
+
+class RemoteCacheRequiredError(DvcException):
+    def __init__(self, path_info):
+        super().__init__(
+            (
+                "Current operation was unsuccessful because '{}' requires "
+                "existing cache on '{}' remote. See {} for information on how "
+                "to set up remote cache."
+            ).format(
+                path_info,
+                path_info.scheme,
+                format_link("https://man.dvc.org/config#cache"),
+            )
+        )
+
+
+class IsADirectoryError(DvcException):
+    """Raised when a file operation is requested on a directory."""

dvc/external_repo.py

@@ -1,29 +1,39 @@
-from __future__ import unicode_literals
-
+import logging
 import os
 import tempfile
+import threading
 from contextlib import contextmanager
 from distutils.dir_util import copy_tree
 
-from funcy import retry
+from funcy import cached_property, retry, suppress, wrap_with
 
-from dvc.config import NoRemoteError, ConfigError
-from dvc.exceptions import NoRemoteInExternalRepoError
-from dvc.remote import RemoteConfig
-from dvc.exceptions import NoOutputInExternalRepoError
-from dvc.exceptions import OutputNotFoundError
-from dvc.utils.fs import remove
+from dvc.config import NoRemoteError, NotDvcRepoError
+from dvc.exceptions import (
+    CheckoutError,
+    FileMissingError,
+    NoOutputInExternalRepoError,
+    NoRemoteInExternalRepoError,
+    OutputNotFoundError,
+    PathMissingError,
+)
+from dvc.path_info import PathInfo
+from dvc.repo import Repo
+from dvc.scm.git import Git
+from dvc.utils import tmp_fname
+from dvc.utils.fs import fs_copy, move, remove
 
-
-REPO_CACHE = {}
+logger = logging.getLogger(__name__)
 
 
 @contextmanager
-def external_repo(url=None, rev=None, rev_lock=None, cache_dir=None):
-    from dvc.repo import Repo
+def external_repo(url, rev=None, for_write=False):
+    logger.debug("Creating external repo %s@%s", url, rev)
+    path = _cached_clone(url, rev, for_write=for_write)
+    try:
+        repo = ExternalRepo(path, url)
+    except NotDvcRepoError:
+        repo = ExternalGitRepo(path, url)
 
-    path = _external_repo(url=url, rev=rev_lock or rev, cache_dir=cache_dir)
-    repo = Repo(path)
     try:
         yield repo
     except NoRemoteError:
@@ -32,90 +42,233 @@ def external_repo(url=None, rev=None, rev_lock=None, cache_dir=None):
         if exc.repo is repo:
             raise NoOutputInExternalRepoError(exc.output, repo.root_dir, url)
         raise
-    repo.close()
-
-
-def _external_repo(url=None, rev=None, cache_dir=None):
-    from dvc.config import Config
-    from dvc.cache import CacheConfig
-    from dvc.repo import Repo
-
-    key = (url, rev, cache_dir)
-    if key in REPO_CACHE:
-        return REPO_CACHE[key]
-
-    new_path = tempfile.mkdtemp("dvc-erepo")
-
-    # Copy and adjust existing clone
-    if (url, None, None) in REPO_CACHE:
-        old_path = REPO_CACHE[url, None, None]
-
-        # This one unlike shutil.copytree() works with an existing dir
-        copy_tree(old_path, new_path)
-    else:
-        # Create a new clone
-        _clone_repo(url, new_path)
-
-        # Save clean clone dir so that we will have access to a default branch
-        clean_clone_path = tempfile.mkdtemp("dvc-erepo")
-        copy_tree(new_path, clean_clone_path)
-        REPO_CACHE[url, None, None] = clean_clone_path
-
-    # Adjust new clone/copy to fit rev and cache_dir
-
-    # Checkout needs to be done first because current branch might not be
-    # DVC repository
-    if rev is not None:
-        _git_checkout(new_path, rev)
-
-    repo = Repo(new_path)
-    try:
-        # 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(url):
-            rconfig = RemoteConfig(repo.config)
-            if not _default_remote_set(rconfig):
-                original_repo = Repo(url)
-                try:
-                    rconfig.add(
-                        "auto-generated-upstream",
-                        original_repo.cache.local.cache_dir,
-                        default=True,
-                        level=Config.LEVEL_LOCAL,
-                    )
-                finally:
-                    original_repo.close()
-
-        if cache_dir is not None:
-            cache_config = CacheConfig(repo.config)
-            cache_config.set_dir(cache_dir, level=Config.LEVEL_LOCAL)
+    except FileMissingError as exc:
+        raise PathMissingError(exc.path, url)
     finally:
-        # Need to close/reopen repo to force config reread
         repo.close()
-
-    REPO_CACHE[key] = new_path
-    return new_path
+        if for_write:
+            _remove(path)
 
 
-def _git_checkout(repo_path, revision):
-    from dvc.scm import Git
-
-    git = Git(repo_path)
-    try:
-        git.checkout(revision)
-    finally:
-        git.close()
+CLONES = {}
+CACHE_DIRS = {}
 
 
 def clean_repos():
     # Outside code should not see cache while we are removing
-    repo_paths = list(REPO_CACHE.values())
-    REPO_CACHE.clear()
+    paths = list(CLONES.values()) + list(CACHE_DIRS.values())
+    CLONES.clear()
+    CACHE_DIRS.clear()
 
-    for path in repo_paths:
+    for path in paths:
         _remove(path)
 
 
+class ExternalRepo(Repo):
+    def __init__(self, root_dir, url):
+        super().__init__(root_dir)
+        self.url = url
+        self._set_cache_dir()
+        self._fix_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(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(path_info, 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))
+
+            try:
+                out.checkout(filter_info=src)
+            except CheckoutError:
+                raise FileNotFoundError
+
+            move(src, dest)
+            remove(tmp)
+
+    @wrap_with(threading.Lock())
+    def _set_cache_dir(self):
+        try:
+            cache_dir = CACHE_DIRS[self.url]
+        except KeyError:
+            cache_dir = CACHE_DIRS[self.url] = tempfile.mkdtemp("dvc-cache")
+
+        self.cache.local.cache_dir = cache_dir
+
+    def _fix_upstream(self):
+        if not os.path.isdir(self.url):
+            return
+
+        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
+        self.url = url
+
+    @cached_property
+    def scm(self):
+        return Git(self.root_dir)
+
+    def close(self):
+        if "scm" in self.__dict__:
+            self.scm.close()
+
+    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), 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."""
+        try:
+            abs_path = os.path.join(self.root_dir, path)
+            with open(abs_path, mode, encoding=encoding) as fd:
+                yield fd
+        except FileNotFoundError:
+            raise PathMissingError(path, self.url)
+
+
+def _cached_clone(url, rev, for_write=False):
+    """Clone an external git repo to a temporary directory.
+
+    Returns the path to a local temporary directory with the specified
+    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]
+
+    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]
+
+    # 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:
+        _git_checkout(repo_path, rev)
+
+    if not for_write:
+        CLONES[url, rev_sha] = repo_path
+    return repo_path
+
+
+@wrap_with(threading.Lock())
+def _clone_default_branch(url, rev):
+    """Get or create a clean clone of the url.
+
+    The cloned is reactualized with git pull unless rev is a known sha.
+    """
+    clone_path = CLONES.get(url)
+
+    git = None
+    try:
+        if clone_path:
+            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
+    finally:
+        if git:
+            git.close()
+
+    return clone_path
+
+
+def _git_checkout(repo_path, rev):
+    logger.debug("erepo: git checkout %s@%s", repo_path, rev)
+    git = Git(repo_path)
+    try:
+        git.checkout(rev)
+    finally:
+        git.close()
+
+
 def _remove(path):
     if os.name == "nt":
         # git.exe may hang for a while not permitting to remove temp dir
@@ -123,26 +276,3 @@ def _remove(path):
         os_retry(remove)(path)
     else:
         remove(path)
-
-
-def _clone_repo(url, path):
-    from dvc.scm.git import Git
-
-    git = Git.clone(url, path)
-    git.close()
-
-
-def _default_remote_set(rconfig):
-    """
-    Checks if default remote config is present.
-    Args:
-        rconfig: a remote config
-
-    Returns:
-        True if the default remote config is set, else False
-    """
-    try:
-        rconfig.get_default()
-        return True
-    except ConfigError:
-        return False

dvc/ignore.py

@@ -1,17 +1,17 @@
-from __future__ import unicode_literals
-
 import logging
 import os
 
+from funcy import cached_property
 from pathspec import PathSpec
 from pathspec.patterns import GitWildMatchPattern
 
+from dvc.scm.tree import BaseTree
 from dvc.utils import relpath
 
 logger = logging.getLogger(__name__)
 
 
-class DvcIgnore(object):
+class DvcIgnore:
     DVCIGNORE_FILE = ".dvcignore"
 
     def __call__(self, root, dirs, files):
@@ -71,14 +71,28 @@ class DvcIgnoreDirs(DvcIgnore):
         return self.basenames == other.basenames
 
 
-class DvcIgnoreFilter(object):
-    def __init__(self, root_dir, 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(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):
         self.tree = tree
-        self.ignores = {DvcIgnoreDirs([".git", ".hg", ".dvc"])}
-        self._update(root_dir)
-        for root, dirs, _ in self.tree.walk(root_dir, dvcignore=self):
-            for d in dirs:
-                self._update(os.path.join(root, d))
+        self.ignores = {
+            DvcIgnoreDirs([".git", ".hg", ".dvc"]),
+            DvcIgnoreRepo(),
+        }
+        for root, dirs, files in self.tree.walk(self.tree.tree_root):
+            self._update(root)
+            dirs[:], files[:] = self(root, dirs, files)
 
     def _update(self, dirname):
         ignore_file_path = os.path.join(dirname, DvcIgnore.DVCIGNORE_FILE)
@@ -90,3 +104,40 @@ class DvcIgnoreFilter(object):
             dirs, files = ignore(root, dirs, files)
 
         return dirs, files
+
+
+class CleanTree(BaseTree):
+    def __init__(self, tree):
+        self.tree = tree
+
+    @cached_property
+    def dvcignore(self):
+        return DvcIgnoreFilter(self.tree)
+
+    @property
+    def tree_root(self):
+        return self.tree.tree_root
+
+    def open(self, path, mode="r", encoding="utf-8"):
+        return self.tree.open(path, mode, encoding)
+
+    def exists(self, path):
+        return self.tree.exists(path)
+
+    def isdir(self, path):
+        return self.tree.isdir(path)
+
+    def isfile(self, path):
+        return self.tree.isfile(path)
+
+    def isexec(self, path):
+        return self.tree.isexec(path)
+
+    def walk(self, top, topdown=True):
+        for root, dirs, files in self.tree.walk(top, topdown):
+            dirs[:], files[:] = self.dvcignore(root, dirs, files)
+
+            yield root, dirs, files
+
+    def stat(self, path):
+        return self.tree.stat(path)

dvc/istextfile.py

@@ -1,24 +1,10 @@
 """Use heuristics to guess if it is a text file or a binary file."""
-from __future__ import unicode_literals
-
-from dvc.utils.compat import is_py3
-from dvc.utils.compat import open
 
 # Based on https://eli.thegreenplace.net/2011/10/19/
 # perls-guess-if-file-is-text-or-binary-implemented-in-python
 
 
-# A function that takes an integer in the 8-bit range and returns
-# a single-character byte object in py3 / a single-character string
-# in py2.
-#
-def _int2byte(i):
-    if is_py3:
-        return bytes((i,))
-    return chr(i)
-
-
-TEXT_CHARS = b"".join(_int2byte(i) for i in range(32, 127)) + b"\n\r\t\f\b"
+TEXT_CHARS = bytes(range(32, 127)) + b"\n\r\t\f\b"
 
 
 def istextfile(fname, blocksize=512):

dvc/lock.py

@@ -1,33 +1,32 @@
 """Manages dvc lock file."""
-from __future__ import unicode_literals
 
 import hashlib
 import os
 import time
 from datetime import timedelta
 
+import flufl.lock
 import zc.lockfile
 
 from dvc.exceptions import DvcException
-from dvc.utils import format_link
-from dvc.utils.compat import is_py3, is_py2
 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."
 )
 
 
 class LockError(DvcException):
-    """Thrown when unable to acquire the lock for dvc repo."""
+    """Thrown when unable to acquire the lock for DVC repo."""
 
 
-class Lock(object):
-    """Class for dvc repo lock.
+class Lock:
+    """Class for DVC repo lock.
 
     Uses zc.lockfile as backend.
     """
@@ -48,7 +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")
                     )
                 ),
             ):
@@ -69,6 +68,10 @@ class Lock(object):
         self._lock.close()
         self._lock = None
 
+    @property
+    def is_locked(self):
+        return bool(self._lock)
+
     def __enter__(self):
         self.lock()
 
@@ -76,83 +79,70 @@ class Lock(object):
         self.unlock()
 
 
-if is_py3:
-    import flufl.lock
+class HardlinkLock(flufl.lock.Lock):
+    """Class for DVC repo lock.
 
-    class HardlinkLock(flufl.lock.Lock):
-        """Class for dvc repo lock.
+    Args:
+        lockfile (str): the lock filename
+            in.
+        tmp_dir (str): a directory to store claim files.
+    """
 
-        Args:
-            lockfile (str): the lock filename
-                in.
-            tmp_dir (str): a directory to store claim files.
-        """
+    def __init__(self, lockfile, tmp_dir=None, **kwargs):
+        import socket
 
-        def __init__(self, lockfile, tmp_dir=None, **kwargs):
-            import socket
+        self._tmp_dir = tmp_dir
 
-            self._tmp_dir = tmp_dir
+        # NOTE: this is basically Lock.__init__ copy-paste, except that
+        # instead of using `socket.getfqdn()` we use `socket.gethostname()`
+        # to speed this up. We've seen [1] `getfqdn()` take ~5sec to return
+        # anything, which is way too slow. `gethostname()` is actually a
+        # fallback for `getfqdn()` when it is not able to resolve a
+        # canonical hostname through network. The claimfile that uses
+        # `self._hostname` is still usable, as it uses `pid` and random
+        # number to generate the resulting lock file name, which is unique
+        # enough for our application.
+        #
+        # [1] https://github.com/iterative/dvc/issues/2582
+        self._hostname = socket.gethostname()
 
-            # NOTE: this is basically Lock.__init__ copy-paste, except that
-            # instead of using `socket.getfqdn()` we use `socket.gethostname()`
-            # to speed this up. We've seen [1] `getfqdn()` take ~5sec to return
-            # anything, which is way too slow. `gethostname()` is actually a
-            # fallback for `getfqdn()` when it is not able to resolve a
-            # canonical hostname through network. The claimfile that uses
-            # `self._hostname` is still usable, as it uses `pid` and random
-            # number to generate the resulting lock file name, which is unique
-            # enough for our application.
-            #
-            # [1] https://github.com/iterative/dvc/issues/2582
-            self._hostname = socket.gethostname()
+        self._lockfile = lockfile
+        self._lifetime = timedelta(days=365)  # Lock for good by default
+        self._separator = flufl.lock.SEP
+        self._set_claimfile()
+        self._owned = True
+        self._retry_errnos = []
 
-            self._lockfile = lockfile
-            self._lifetime = timedelta(days=365)  # Lock for good by default
-            self._separator = flufl.lock.SEP
-            self._set_claimfile()
-            self._owned = True
-            self._retry_errnos = []
+    @property
+    def lockfile(self):
+        return self._lockfile
 
-        @property
-        def lockfile(self):
-            return self._lockfile
+    def lock(self):
+        try:
+            super().lock(timedelta(seconds=DEFAULT_TIMEOUT))
+        except flufl.lock.TimeOutError:
+            raise LockError(FAILED_TO_LOCK_MESSAGE)
 
-        def lock(self):
-            try:
-                super(Lock, self).lock(timedelta(seconds=DEFAULT_TIMEOUT))
-            except flufl.lock.TimeOutError:
-                raise LockError(FAILED_TO_LOCK_MESSAGE)
+    def _set_claimfile(self, pid=None):
+        super()._set_claimfile(pid)
 
-        def _set_claimfile(self, pid=None):
-            super(Lock, self)._set_claimfile(pid)
+        if self._tmp_dir is not None:
+            # Under Windows file path length is limited so we hash it
+            filename = hashlib.md5(self._claimfile.encode()).hexdigest()
+            self._claimfile = os.path.join(self._tmp_dir, filename + ".lock")
 
-            if self._tmp_dir is not None:
-                # Under Windows file path length is limited so we hash it
-                filename = hashlib.md5(self._claimfile.encode()).hexdigest()
-                self._claimfile = os.path.join(
-                    self._tmp_dir, filename + ".lock"
-                )
-
-        # Fix for __del__ bug in flufl.lock [1] which is causing errors on
-        # Python shutdown [2].
-        # [1] https://gitlab.com/warsaw/flufl.lock/issues/7
-        # [2] https://github.com/iterative/dvc/issues/2573
-        def __del__(self):
-            try:
-                if self._owned:
-                    self.finalize()
-            except ImportError:
-                pass
+    # Fix for __del__ bug in flufl.lock [1] which is causing errors on
+    # Python shutdown [2].
+    # [1] https://gitlab.com/warsaw/flufl.lock/issues/7
+    # [2] https://github.com/iterative/dvc/issues/2573
+    def __del__(self):
+        try:
+            if self._owned:
+                self.finalize()
+        except ImportError:
+            pass
 
 
 def make_lock(lockfile, tmp_dir=None, friendly=False, hardlink_lock=False):
-    if hardlink_lock and is_py2:
-        raise DvcException(
-            "Hardlink locks are not supported on Python <3.5. "
-            "See `hardlink_lock` in {}".format(
-                format_link("man.dvc.org/config#core")
-            )
-        )
-
     cls = HardlinkLock if hardlink_lock else Lock
     return cls(lockfile, tmp_dir=tmp_dir, friendly=friendly)

dvc/logger.py

@@ -1,5 +1,4 @@
-"""Manages logging configuration for dvc repo."""
-from __future__ import unicode_literals
+"""Manages logging configuration for DVC repo."""
 
 import logging.config
 import logging.handlers
@@ -7,10 +6,6 @@ import logging.handlers
 import colorama
 
 from dvc.progress import Tqdm
-from dvc.utils.compat import RecursionError
-from dvc.utils.compat import str
-from dvc.utils.compat import StringIO
-
 
 FOOTER = (
     "\n{yellow}Having any troubles?{nc}"
@@ -26,7 +21,7 @@ FOOTER = (
 class LoggingException(Exception):
     def __init__(self, record):
         msg = "failed to log {}".format(str(record))
-        super(LoggingException, self).__init__(msg)
+        super().__init__(msg)
 
 
 class ExcludeErrorsFilter(logging.Filter):
@@ -40,117 +35,70 @@ class ExcludeInfoFilter(logging.Filter):
 
 
 class ColorFormatter(logging.Formatter):
-    """Enable color support when logging to a terminal that supports it.
+    """Spit out colored text in supported terminals.
 
-    Color support on Windows versions that do not support ANSI color codes is
-    enabled by use of the colorama__ library.
+    colorama__ makes ANSI escape character sequences work under Windows.
     See the colorama documentation for details.
 
     __ https://pypi.python.org/pypi/colorama
 
-    For records containing `exc_info`, it will use a custom `_walk_exc` to
-    retrieve the whole traceback.
+    If record has an extra `tb_only` attribute, it will not show the
+    exception cause, just the message and the traceback.
     """
 
     color_code = {
         "DEBUG": colorama.Fore.BLUE,
-        "INFO": "",
         "WARNING": colorama.Fore.YELLOW,
         "ERROR": colorama.Fore.RED,
         "CRITICAL": colorama.Fore.RED,
     }
 
     def format(self, record):
+        record.message = record.getMessage()
+        msg = self.formatMessage(record)
+
         if record.levelname == "INFO":
-            return record.msg
+            return msg
 
-        if record.levelname == "ERROR" or record.levelname == "CRITICAL":
-            exception, stack_trace = self._parse_exc(record.exc_info)
+        if record.exc_info:
+            if getattr(record, "tb_only", False):
+                cause = ""
+            else:
+                cause = ": ".join(_iter_causes(record.exc_info[1]))
 
-            return (
-                "{color}{levelname}{nc}: {description}" "{stack_trace}\n"
-            ).format(
-                color=self.color_code.get(record.levelname, ""),
-                nc=colorama.Fore.RESET,
-                levelname=record.levelname,
-                description=self._description(record.msg, exception),
-                msg=record.msg,
-                stack_trace=stack_trace,
+            msg = "{message}{separator}{cause}".format(
+                message=msg or "",
+                separator=" - " if msg and cause else "",
+                cause=cause,
             )
 
-        return "{color}{levelname}{nc}: {msg}".format(
-            color=self.color_code.get(record.levelname, ""),
+            if _is_verbose():
+                msg += _stack_trace(record.exc_info)
+
+        return "{asctime}{color}{levelname}{nc}: {msg}".format(
+            asctime=self.formatTime(record, self.datefmt),
+            color=self.color_code[record.levelname],
             nc=colorama.Fore.RESET,
             levelname=record.levelname,
-            msg=record.msg,
+            msg=msg,
         )
 
-    def _current_level(self):
-        return logging.getLogger("dvc").getEffectiveLevel()
+    def formatTime(self, record, datefmt=None):
+        # only show if current level is set to DEBUG
+        # also, skip INFO as it is used for UI
+        if not _is_verbose() or record.levelno == logging.INFO:
+            return ""
 
-    def _is_visible(self, record):
-        return record.levelno >= self._current_level()
-
-    def _description(self, message, exception):
-        description = ""
-
-        if exception and message:
-            description = "{message} - {exception}"
-        elif exception:
-            description = "{exception}"
-        elif message:
-            description = "{message}"
-
-        return description.format(message=message, exception=exception)
-
-    def _walk_exc(self, exc_info):
-        import traceback
-
-        buffer = StringIO()
-
-        traceback.print_exception(*exc_info, file=buffer)
-
-        exc = exc_info[1]
-        tb = buffer.getvalue()
-
-        exc_list = [str(exc)]
-        tb_list = [tb]
-
-        # NOTE: parsing chained exceptions. See dvc/exceptions.py for more info
-        while hasattr(exc, "cause") and exc.cause:
-            exc_list.append(str(exc.cause))
-            if hasattr(exc, "cause_tb") and exc.cause_tb:
-                tb_list.insert(0, str(exc.cause_tb))
-            exc = exc.cause
-
-        return exc_list, tb_list
-
-    def _parse_exc(self, exc_info):
-        if not exc_info:
-            return (None, "")
-
-        exc_list, tb_list = self._walk_exc(exc_info)
-
-        exception = ": ".join(exc_list)
-
-        if self._current_level() == logging.DEBUG:
-            stack_trace = (
-                "\n" "{red}{line}{nc}\n" "{stack_trace}" "{red}{line}{nc}"
-            ).format(
-                red=colorama.Fore.RED,
-                nc=colorama.Fore.RESET,
-                line="-" * 60,
-                stack_trace="\n".join(tb_list),
-            )
-        else:
-            stack_trace = ""
-
-        return (exception, stack_trace)
+        return "{green}{date}{nc} ".format(
+            green=colorama.Fore.GREEN,
+            date=super().formatTime(record, datefmt),
+            nc=colorama.Fore.RESET,
+        )
 
 
 class LoggerHandler(logging.StreamHandler):
     def handleError(self, record):
-        super(LoggerHandler, self).handleError(record)
+        super().handleError(record)
         raise LoggingException(record)
 
     def emit(self, record):
@@ -167,6 +115,40 @@ class LoggerHandler(logging.StreamHandler):
             self.handleError(record)
 
 
+def _is_verbose():
+    return logging.getLogger("dvc").getEffectiveLevel() == logging.DEBUG
+
+
+def _iter_causes(exc):
+    while exc:
+        yield str(exc)
+        exc = exc.__cause__
+
+
+def _stack_trace(exc_info):
+    import traceback
+
+    return (
+        "\n"
+        "{red}{line}{nc}\n"
+        "{trace}"
+        "{red}{line}{nc}".format(
+            red=colorama.Fore.RED,
+            line="-" * 60,
+            trace="".join(traceback.format_exception(*exc_info)),
+            nc=colorama.Fore.RESET,
+        )
+    )
+
+
+def disable_other_loggers():
+    logging.captureWarnings(True)
+    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()
 
@@ -209,22 +191,7 @@ def setup(level=logging.INFO):
                         "console_errors",
                     ],
                 },
-                "paramiko": {
-                    "level": logging.CRITICAL,
-                    "handlers": [
-                        "console_info",
-                        "console_debug",
-                        "console_errors",
-                    ],
-                },
-                "flufl.lock": {
-                    "level": logging.CRITICAL,
-                    "handlers": [
-                        "console_info",
-                        "console_debug",
-                        "console_errors",
-                    ],
-                },
             },
+            "disable_existing_loggers": False,
         }
     )

dvc/main.py

@@ -1,5 +1,4 @@
 """Main entry point for dvc CLI."""
-from __future__ import unicode_literals
 
 import errno
 import logging
@@ -7,17 +6,16 @@ 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.logger import FOOTER, disable_other_loggers
 from dvc.remote.pool import close_pools
-from dvc.utils.compat import is_py2
-
+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
 # [2] https://bugs.python.org/issue29288
+
 "".encode("idna")
 
 
@@ -34,7 +32,7 @@ def main(argv=None):
         int: command's return code.
     """
     args = None
-    cmd = None
+    disable_other_loggers()
 
     outerLogLevel = logger.level
     try:
@@ -59,15 +57,18 @@ def main(argv=None):
         ret = 253
     except DvcParserError:
         ret = 254
+    except DvcException:
+        ret = 255
+        logger.exception("")
     except Exception as exc:  # pylint: disable=broad-except
-        if isinstance(exc, UnicodeError) and is_py2:
+        if isinstance(exc, OSError) and exc.errno == errno.EMFILE:
             logger.exception(
-                "unicode is not supported in DVC for Python 2 "
-                "(end-of-life January 1, 2020), please upgrade to Python 3"
-            )
-        elif isinstance(exc, OSError) and exc.errno == errno.EMFILE:
-            logger.exception(
-                "too many open files, please increase your `ulimit`"
+                "too many open files, please visit "
+                "{} to see how to handle this "
+                "problem".format(
+                    format_link("https://error.dvc.org/many-files")
+                ),
+                extra={"tb_only": True},
             )
         else:
             logger.exception("unexpected error")
@@ -75,8 +76,9 @@ def main(argv=None):
     finally:
         logger.setLevel(outerLogLevel)
 
-        # Python 2 fails to close these clean occasionally and users see
-        # weird error messages, so we do it manually
+        # Closing pools by-hand to prevent wierd messages when closing SSH
+        # connections. See https://github.com/iterative/dvc/issues/3248 for
+        # more info.
         close_pools()
 
         # Remove cached repos in the end of the call, these are anonymous

dvc/output/__init__.py

@@ -1,37 +1,41 @@
-from __future__ import unicode_literals
+from urllib.parse import urlparse
 
-from voluptuous import Any, Required
+from voluptuous import And, Any, Coerce, Length, Lower, Required, 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.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 Remote
-from dvc.remote.hdfs import RemoteHDFS
-from dvc.remote.local import RemoteLOCAL
-from dvc.remote.s3 import RemoteS3
+from dvc.remote.hdfs import HDFSRemote
+from dvc.remote.local import LocalRemote
+from dvc.remote.s3 import S3Remote
 from dvc.scheme import Schemes
-from dvc.utils.compat import str
-from dvc.utils.compat import urlparse
 
 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(
+    None,
+    And(str, Length(max=0), SetTo(None)),
+    And(Any(str, And(int, Coerce(str))), Length(min=3), Lower),
+)
+
 # NOTE: currently there are only 3 possible checksum names:
 #
 #    1) md5 (LOCAL, SSH, GS);
@@ -40,23 +44,21 @@ OUTS_MAP = {
 #
 # so when a few types of outputs share the same name, we only need
 # specify it once.
-CHECKSUM_SCHEMA = {
-    RemoteLOCAL.PARAM_CHECKSUM: Any(str, None),
-    RemoteS3.PARAM_CHECKSUM: Any(str, None),
-    RemoteHDFS.PARAM_CHECKSUM: Any(str, None),
+CHECKSUMS_SCHEMA = {
+    LocalRemote.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
+    S3Remote.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
+    HDFSRemote.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
 }
 
-TAGS_SCHEMA = {str: CHECKSUM_SCHEMA}
-
-SCHEMA = CHECKSUM_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 = CHECKSUMS_SCHEMA.copy()
+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, cache, metric, plot=False, persist=False):
     parsed = urlparse(p)
 
     if parsed.scheme == "remote":
@@ -68,8 +70,8 @@ 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:
@@ -81,29 +83,29 @@ 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,
@@ -111,24 +113,25 @@ 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
+    ]

dvc/output/base.py

@@ -1,57 +1,57 @@
-from __future__ import unicode_literals
-
 import logging
+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
-from dvc.exceptions import DvcException
-from dvc.remote.base import RemoteBASE
-from dvc.utils.compat import str
-from dvc.utils.compat import urlparse
-
+from dvc.exceptions import (
+    CollectCacheError,
+    DvcException,
+    RemoteCacheRequiredError,
+)
+from dvc.remote.base import BaseRemote
 
 logger = logging.getLogger(__name__)
 
 
 class OutputDoesNotExistError(DvcException):
     def __init__(self, path):
-        msg = "output '{}' does not exist".format(path)
-        super(OutputDoesNotExistError, self).__init__(msg)
+        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)
-        super(OutputIsNotFileOrDirError, self).__init__(msg)
+        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)
-        super(OutputAlreadyTrackedError, self).__init__(msg)
+        msg = f"output '{path}' is already tracked by SCM (e.g. Git)"
+        super().__init__(msg)
 
 
 class OutputIsStageFileError(DvcException):
     def __init__(self, path):
-        super(OutputIsStageFileError, self).__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 = BaseRemote
 
     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_PERSIST = "persist"
 
     METRIC_SCHEMA = Any(
@@ -63,8 +63,6 @@ class OutputBase(object):
         },
     )
 
-    PARAM_TAGS = "tags"
-
     DoesNotExistError = OutputDoesNotExistError
     IsNotFileOrDirError = OutputIsNotFileOrDirError
     IsStageFileError = OutputIsStageFileError
@@ -79,8 +77,8 @@ 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
@@ -100,17 +98,12 @@ class OutputBase(object):
         self.remote = remote or self.REMOTE(self.repo, {})
         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 {})
-
-        if self.use_cache and self.cache is None:
-            raise DvcException(
-                "no cache location setup for '{}' outputs.".format(
-                    self.REMOTE.scheme
-                )
-            )
 
         self.path_info = self._parse_path(remote, path)
+        if self.use_cache and self.cache is None:
+            raise RemoteCacheRequiredError(self.path_info)
 
     def _parse_path(self, remote, path):
         if remote:
@@ -157,10 +150,21 @@ class OutputBase(object):
     def cache_path(self):
         return self.cache.checksum_to_path_info(self.checksum).url
 
+    @property
+    def checksum_type(self):
+        return self.remote.PARAM_CHECKSUM
+
     @property
     def checksum(self):
         return self.info.get(self.remote.PARAM_CHECKSUM)
 
+    @checksum.setter
+    def checksum(self, checksum):
+        self.info[self.remote.PARAM_CHECKSUM] = checksum
+
+    def get_checksum(self):
+        return self.remote.get_checksum(self.path_info)
+
     @property
     def is_dir_checksum(self):
         return self.remote.is_dir_checksum(self.checksum)
@@ -169,14 +173,17 @@ class OutputBase(object):
     def exists(self):
         return self.remote.exists(self.path_info)
 
-    def changed_checksum(self):
-        return self.checksum != self.remote.get_checksum(self.path_info)
+    def save_info(self):
+        return self.remote.save_info(self.path_info)
 
-    def changed_cache(self):
+    def changed_checksum(self):
+        return self.checksum != self.get_checksum()
+
+    def changed_cache(self, filter_info=None):
         if not self.use_cache or not self.checksum:
             return True
 
-        return self.cache.changed_cache(self.checksum)
+        return self.cache.changed_cache(self.checksum, filter_info=filter_info)
 
     def status(self):
         if self.checksum and self.use_cache and self.changed_cache():
@@ -208,6 +215,15 @@ class OutputBase(object):
     def isfile(self):
         return self.remote.isfile(self.path_info)
 
+    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 save(self):
         if not self.exists:
             raise self.DoesNotExistError(self)
@@ -216,17 +232,13 @@ 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.repo.scm.ignore(self.fspath)
+        self.ignore()
 
         if not self.use_cache:
-            self.info = self.remote.save_info(self.path_info)
-            if self.metric:
+            self.info = self.save_info()
+            if self.metric or self.plot:
                 self.verify_metric()
             if not self.IS_DEPENDENCY:
                 logger.info(
@@ -239,12 +251,10 @@ class OutputBase(object):
         assert not self.IS_DEPENDENCY
 
         if not self.changed():
-            logger.info(
-                "Output '{}' didn't change. Skipping saving.".format(self)
-            )
+            logger.info(f"Output '{self}' didn't change. Skipping saving.")
             return
 
-        self.info = self.remote.save_info(self.path_info)
+        self.info = self.save_info()
 
     def commit(self):
         if self.use_cache:
@@ -267,40 +277,41 @@ class OutputBase(object):
                 del self.metric[self.PARAM_METRIC_XPATH]
 
         ret[self.PARAM_METRIC] = self.metric
-        ret[self.PARAM_PERSIST] = self.persist
 
-        if self.tags:
-            ret[self.PARAM_TAGS] = self.tags
+        if self.plot:
+            ret[self.PARAM_PLOT] = self.plot
+
+        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)
 
     def checkout(
-        self, force=False, progress_callback=None, tag=None, relink=False
+        self,
+        force=False,
+        progress_callback=None,
+        relink=False,
+        filter_info=None,
     ):
         if not self.use_cache:
             if progress_callback:
-                progress_callback(str(self.path_info), self.get_files_number())
+                progress_callback(
+                    str(self.path_info), self.get_files_number(filter_info)
+                )
             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,
+            filter_info=filter_info,
         )
 
     def remove(self, ignore_remove=False):
@@ -324,17 +335,21 @@ class OutputBase(object):
         if self.scheme == "local" and self.use_scm_ignore:
             self.repo.scm.ignore(self.fspath)
 
-    def get_files_number(self):
+    def get_files_number(self, filter_info=None):
         if not self.use_cache:
             return 0
 
-        return self.cache.get_files_number(self.checksum)
+        return self.cache.get_files_number(
+            self.path_info, self.checksum, filter_info
+        )
 
     def unprotect(self):
         if self.exists:
             self.remote.unprotect(self.path_info)
 
-    def _collect_used_dir_cache(self, remote=None, force=False, jobs=None):
+    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.
 
         - Pull the directory entry from the remote cache if it was changed.
@@ -365,7 +380,7 @@ class OutputBase(object):
                     show_checksums=False,
                 )
             except DvcException:
-                logger.debug("failed to pull cache for '{}'".format(self))
+                logger.debug(f"failed to pull cache for '{self}'")
 
         if self.cache.changed_cache_file(self.checksum):
             msg = (
@@ -381,10 +396,21 @@ 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]
-            path_info = self.path_info / entry[self.remote.PARAM_RELPATH]
-            cache.add(self.scheme, checksum, str(path_info))
+            entry_relpath = entry[self.remote.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
 
@@ -400,12 +426,29 @@ class OutputBase(object):
         if not self.use_cache:
             return NamedCache()
 
-        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 self.stage.is_repo_import:
+            cache = NamedCache()
+            (dep,) = self.stage.deps
+            cache.external[dep.repo_pair].add(dep.def_path)
+            return cache
+
+        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))
@@ -413,13 +456,15 @@ 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

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-from dvc.output.s3 import OutputS3
-from dvc.remote.gs import RemoteGS
+from dvc.output.s3 import S3Output
+from dvc.remote.gs import GSRemote
 
 
-class OutputGS(OutputS3):
-    REMOTE = RemoteGS
+class GSOutput(S3Output):
+    REMOTE = GSRemote

dvc/output/hdfs.py

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-from dvc.output.base import OutputBase
-from dvc.remote.hdfs import RemoteHDFS
+from dvc.output.base import BaseOutput
+from dvc.remote.hdfs import HDFSRemote
 
 
-class OutputHDFS(OutputBase):
-    REMOTE = RemoteHDFS
+class HDFSOutput(BaseOutput):
+    REMOTE = HDFSRemote

dvc/output/local.py

@@ -1,26 +1,27 @@
-from __future__ import unicode_literals
-
 import logging
 import os
+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
 from dvc.utils import relpath
-from dvc.utils.compat import fspath_py35
-from dvc.utils.compat import str
-from dvc.utils.compat import urlparse
 from dvc.utils.fs import path_isin
 
-
 logger = logging.getLogger(__name__)
 
 
-class OutputLOCAL(OutputBase):
-    REMOTE = RemoteLOCAL
+class LocalOutput(BaseOutput):
+    REMOTE = LocalRemote
     sep = os.sep
 
+    def __init__(self, stage, path, *args, **kwargs):
+        if stage and path_isin(path, stage.repo.root_dir):
+            path = relpath(path, stage.wdir)
+
+        super().__init__(stage, path, *args, **kwargs)
+
     def _parse_path(self, remote, path):
         parsed = urlparse(path)
         if parsed.scheme == "remote":
@@ -36,7 +37,7 @@ class OutputLOCAL(OutputBase):
             if not p.is_absolute():
                 p = self.stage.wdir / p
 
-        abs_p = os.path.abspath(os.path.normpath(fspath_py35(p)))
+        abs_p = os.path.abspath(os.path.normpath(p))
         return self.REMOTE.path_cls(abs_p)
 
     def __str__(self):
@@ -59,7 +60,7 @@ class OutputLOCAL(OutputBase):
         return def_scheme != "remote" and not os.path.isabs(self.def_path)
 
     def dumpd(self):
-        ret = super(OutputLOCAL, self).dumpd()
+        ret = super().dumpd()
         if self.is_in_repo:
             path = self.path_info.relpath(self.stage.wdir).as_posix()
         else:
@@ -70,17 +71,18 @@ 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 DvcException(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

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-from dvc.output.base import OutputBase
-from dvc.remote.s3 import RemoteS3
+from dvc.output.base import BaseOutput
+from dvc.remote.s3 import S3Remote
 
 
-class OutputS3(OutputBase):
-    REMOTE = RemoteS3
+class S3Output(BaseOutput):
+    REMOTE = S3Remote

dvc/output/ssh.py

@@ -1,8 +1,6 @@
-from __future__ import unicode_literals
-
-from dvc.output.base import OutputBase
-from dvc.remote.ssh import RemoteSSH
+from dvc.output.base import BaseOutput
+from dvc.remote.ssh import SSHRemote
 
 
-class OutputSSH(OutputBase):
-    REMOTE = RemoteSSH
+class SSHOutput(BaseOutput):
+    REMOTE = SSHRemote

dvc/path_info.py

@@ -1,35 +1,23 @@
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 import os
+import pathlib
 import posixpath
-import sys
+from urllib.parse import urlparse
 
 from funcy import cached_property
 
 from dvc.utils import relpath
-from dvc.utils.compat import basestring
-from dvc.utils.compat import builtin_str
-from dvc.utils.compat import is_py2
-from dvc.utils.compat import pathlib
-from dvc.utils.compat import str
-from dvc.utils.compat import urlparse
 
 
-# On Python 2.7/Windows sys.getfilesystemencoding() is set to mbcs,
-# which is lossy, thus we can't use that,
-# see https://github.com/mcmtroffaes/pathlib2/issues/56.
-if is_py2:
-    fs_encoding = "utf-8"
-
-
-class _BasePath(object):
+class _BasePath:
     def overlaps(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         elif self.__class__ != other.__class__:
             return False
-        return self == other or self.isin(other) or other.isin(self)
+        return self.isin_or_eq(other) or other.isin(self)
+
+    def isin_or_eq(self, other):
+        return self == other or self.isin(other)
 
 
 class PathInfo(pathlib.PurePath, _BasePath):
@@ -45,10 +33,6 @@ class PathInfo(pathlib.PurePath, _BasePath):
             cls = 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
         # Unlike original implementation [1] that uses `str()` we actually need
@@ -63,10 +47,9 @@ class PathInfo(pathlib.PurePath, _BasePath):
         return relpath(path)
 
     def __repr__(self):
-        return builtin_str("{}: '{}'").format(type(self).__name__, self)
+        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)
 
@@ -80,7 +63,7 @@ class PathInfo(pathlib.PurePath, _BasePath):
         return self.__class__(relpath(self, other))
 
     def isin(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         elif self.__class__ != other.__class__:
             return False
@@ -88,34 +71,6 @@ class PathInfo(pathlib.PurePath, _BasePath):
         n = len(other._cparts)
         return len(self._cparts) > n and self._cparts[:n] == other._cparts
 
-    # pathlib2 uses bytes internally in Python 2, and we use unicode everywhere
-    # for paths in both pythons, thus we need this glue.
-    if is_py2:
-        __unicode__ = __str__
-
-        def __str__(self):
-            return self.__unicode__().encode(sys.getfilesystemencoding())
-
-        @classmethod
-        def _parse_args(cls, args):
-            args = [
-                a.encode(fs_encoding)
-                if isinstance(a, unicode)  # noqa: F821
-                else a
-                for a in args
-            ]
-            return super(PathInfo, cls)._parse_args(args)
-
-        @property
-        def name(self):
-            return super(PathInfo, self).name.decode(fs_encoding)
-
-        def __fspath__(self):  # noqa: F811
-            return pathlib.PurePath.__str__(self).decode(fs_encoding)
-
-        def with_name(self, name):
-            return pathlib.PurePath.with_name(self, name.encode(fs_encoding))
-
 
 class WindowsPathInfo(PathInfo, pathlib.PureWindowsPath):
     pass
@@ -132,7 +87,7 @@ class _URLPathInfo(PosixPathInfo):
     __unicode__ = __str__
 
 
-class _URLPathParents(object):
+class _URLPathParents:
     def __init__(self, src):
         self.src = src
         self._parents = self.src._path.parents
@@ -144,7 +99,7 @@ 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):
@@ -155,7 +110,7 @@ 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(
@@ -164,21 +119,21 @@ 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, (basestring, _URLPathInfo))
+        assert isinstance(path, (str, bytes, _URLPathInfo))
 
         self.scheme, self.host, self.user = scheme, host, user
         self.port = int(port) if port else self.DEFAULT_PORTS.get(self.scheme)
 
         if isinstance(path, _URLPathInfo):
-            self._spath = builtin_str(path)
+            self._spath = str(path)
             self._path = path
         else:
             if path and path[0] != "/":
@@ -198,7 +153,7 @@ 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
@@ -207,7 +162,7 @@ class URLInfo(_BasePath):
         return "{}: '{}'".format(type(self).__name__, self)
 
     def __eq__(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         return (
             self.__class__ == other.__class__
@@ -257,18 +212,18 @@ class URLInfo(_BasePath):
         return _URLPathParents(self)
 
     def relative_to(self, other):
-        if isinstance(other, basestring):
+        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)
 
     def isin(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         elif self.__class__ != other.__class__:
             return False
@@ -281,3 +236,78 @@ 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,
+    ):
+        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

@@ -1,11 +1,9 @@
-"""Manages progress bars for dvc repo."""
-from __future__ import print_function
+"""Manages progress bars for DVC repo."""
 
 import logging
 import sys
 from threading import RLock
 
-from funcy import merge
 from tqdm import tqdm
 
 from dvc.utils import env2bool
@@ -21,18 +19,20 @@ 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
     )
 
     def __init__(
@@ -45,6 +45,8 @@ class Tqdm(tqdm):
         bar_format=None,
         bytes=False,  # pylint: disable=W0622
         file=None,
+        total=None,
+        postfix=None,
         **kwargs
     ):
         """
@@ -53,23 +55,21 @@ class Tqdm(tqdm):
         desc  : persists after `close()`
         level  : effective logging level for determining `disable`;
             used only if `disable` is unspecified
-        disable  : If (default: None), will be determined by logging level.
+        disable  : If (default: None) or False,
+            will be determined by logging level.
             May be overridden to `True` due to non-TTY status.
             Skip override by specifying env var `DVC_IGNORE_ISATTY`.
         kwargs  : anything accepted by `tqdm.tqdm()`
         """
         kwargs = kwargs.copy()
-        kwargs.setdefault("unit_scale", True)
         if bytes:
-            bytes_defaults = dict(
-                unit="B", unit_scale=True, unit_divisor=1024, miniters=1
-            )
-            kwargs = merge(bytes_defaults, kwargs)
+            kwargs = {**self.BYTES_DEFAULTS, **kwargs}
+        else:
+            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 disable is None:
+        if not disable:
             disable = logger.getEffectiveLevel() > level
         # auto-disable based on TTY
         if (
@@ -78,15 +78,17 @@ class Tqdm(tqdm):
             and hasattr(file, "isatty")
         ):
             disable = not file.isatty()
-        super(Tqdm, self).__init__(
+        super().__init__(
             iterable=iterable,
             disable=disable,
             leave=leave,
             desc=desc,
             bar_format="!",
             lock_args=(False,),
+            total=total,
             **kwargs
         )
+        self.postfix = postfix or {"info": ""}
         if bar_format is None:
             if self.__len__():
                 self.bar_format = (
@@ -100,11 +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):
@@ -112,22 +114,43 @@ 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)
-        super(Tqdm, self).close()
+        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
     def format_dict(self):
         """inject `ncols_desc` to fill the display width (`ncols`)"""
-        d = super(Tqdm, self).format_dict
+        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

@@ -1,14 +1,9 @@
 """Manages user prompts."""
-from __future__ import print_function
-from __future__ import unicode_literals
 
 import logging
 import sys
 from getpass import getpass
 
-from dvc.utils.compat import input
-
-
 logger = logging.getLogger(__name__)
 
 
@@ -43,7 +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")
 
@@ -57,5 +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

@@ -1,44 +1,74 @@
-from __future__ import unicode_literals
-
-from .config import RemoteConfig
-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
+import posixpath
+from urllib.parse import urlparse
 
+from dvc.remote.azure import AzureRemote
+from dvc.remote.gdrive import GDriveRemote
+from dvc.remote.gs import GSRemote
+from dvc.remote.hdfs import HDFSRemote
+from dvc.remote.http import HTTPRemote
+from dvc.remote.https import HTTPSRemote
+from dvc.remote.local import LocalRemote
+from dvc.remote.oss import OSSRemote
+from dvc.remote.s3 import S3Remote
+from dvc.remote.ssh import SSHRemote
 
 REMOTES = [
-    RemoteAZURE,
-    RemoteGDrive,
-    RemoteGS,
-    RemoteHDFS,
-    RemoteHTTP,
-    RemoteHTTPS,
-    RemoteS3,
-    RemoteSSH,
-    RemoteOSS,
-    # NOTE: RemoteLOCAL is the default
+    AzureRemote,
+    GDriveRemote,
+    GSRemote,
+    HDFSRemote,
+    HTTPRemote,
+    HTTPSRemote,
+    S3Remote,
+    SSHRemote,
+    OSSRemote,
+    # NOTE: LocalRemote is the default
 ]
 
 
-def _get(config):
+def _get(remote_conf):
     for remote in REMOTES:
-        if remote.supported(config):
+        if remote.supported(remote_conf):
             return remote
-    return RemoteLOCAL
+    return LocalRemote
 
 
 def Remote(repo, **kwargs):
     name = kwargs.get("name")
     if name:
-        remote_config = RemoteConfig(repo.config)
-        settings = remote_config.get_settings(name)
+        remote_conf = repo.config["remote"][name.lower()]
     else:
-        settings = kwargs
-    return _get(settings)(repo, settings)
+        remote_conf = kwargs
+    remote_conf = _resolve_remote_refs(repo.config, remote_conf)
+    return _get(remote_conf)(repo, remote_conf)
+
+
+def _resolve_remote_refs(config, remote_conf):
+    # Support for cross referenced remotes.
+    # This will merge the settings, shadowing base ref with remote_conf.
+    # For example, having:
+    #
+    #       dvc remote add server ssh://localhost
+    #       dvc remote modify server user root
+    #       dvc remote modify server ask_password true
+    #
+    #       dvc remote add images remote://server/tmp/pictures
+    #       dvc remote modify images user alice
+    #       dvc remote modify images ask_password false
+    #       dvc remote modify images password asdf1234
+    #
+    # Results on a config dictionary like:
+    #
+    #       {
+    #           "url": "ssh://localhost/tmp/pictures",
+    #           "user": "alice",
+    #           "password": "asdf1234",
+    #           "ask_password": False,
+    #       }
+    parsed = urlparse(remote_conf["url"])
+    if parsed.scheme != "remote":
+        return remote_conf
+
+    base = config["remote"][parsed.netloc]
+    url = posixpath.join(base["url"], parsed.path.lstrip("/"))
+    return {**base, **remote_conf, "url": url}

dvc/remote/azure.py

@@ -1,26 +1,22 @@
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 import logging
 import os
+import posixpath
 import re
-from datetime import datetime, timedelta
 import threading
+from datetime import datetime, timedelta
+from urllib.parse import urlparse
 
 from funcy import cached_property, wrap_prop
 
-from dvc.config import Config
 from dvc.path_info import CloudURLInfo
 from dvc.progress import Tqdm
-from dvc.remote.base import RemoteBASE
+from dvc.remote.base import BaseRemote
 from dvc.scheme import Schemes
-from dvc.utils.compat import urlparse
-
 
 logger = logging.getLogger(__name__)
 
 
-class RemoteAZURE(RemoteBASE):
+class AzureRemote(BaseRemote):
     scheme = Schemes.AZURE
     path_cls = CloudURLInfo
     REGEX = (
@@ -32,11 +28,12 @@ class RemoteAZURE(RemoteBASE):
     REQUIRES = {"azure-storage-blob": "azure.storage.blob"}
     PARAM_CHECKSUM = "etag"
     COPY_POLL_SECONDS = 5
+    LIST_OBJECT_PAGE_SIZE = 5000
 
     def __init__(self, repo, config):
-        super(RemoteAZURE, self).__init__(repo, config)
+        super().__init__(repo, config)
 
-        url = config.get(Config.SECTION_REMOTE_URL, "azure://")
+        url = config.get("url", "azure://")
 
         match = re.match(self.REGEX, url)  # backward compatibility
         path = match.group("path")
@@ -47,7 +44,7 @@ class RemoteAZURE(RemoteBASE):
         )
 
         self.connection_string = (
-            config.get(Config.SECTION_AZURE_CONNECTION_STRING)
+            config.get("connection_string")
             or match.group("connection_string")  # backward compatibility
             or os.getenv("AZURE_STORAGE_CONNECTION_STRING")
         )
@@ -70,12 +67,12 @@ class RemoteAZURE(RemoteBASE):
         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))
+        logger.debug(f"URL {self.path_info}")
+        logger.debug(f"Connection string {self.connection_string}")
         blob_service = BlockBlobService(
             connection_string=self.connection_string
         )
-        logger.debug("Container name {}".format(self.path_info.bucket))
+        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
@@ -88,10 +85,10 @@ class RemoteAZURE(RemoteBASE):
         if path_info.scheme != self.scheme:
             raise NotImplementedError
 
-        logger.debug("Removing {}".format(path_info))
+        logger.debug(f"Removing {path_info}")
         self.blob_service.delete_blob(path_info.bucket, path_info.path)
 
-    def _list_paths(self, bucket, prefix):
+    def _list_paths(self, bucket, prefix, progress_callback=None):
         blob_service = self.blob_service
         next_marker = None
         while True:
@@ -100,6 +97,8 @@ class RemoteAZURE(RemoteBASE):
             )
 
             for blob in blobs:
+                if progress_callback:
+                    progress_callback()
                 yield blob.name
 
             if not blobs.next_marker:
@@ -107,8 +106,16 @@ 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 list_cache_paths(self, prefix=None, progress_callback=None):
+        if prefix:
+            prefix = posixpath.join(
+                self.path_info.path, prefix[:2], prefix[2:]
+            )
+        else:
+            prefix = self.path_info.path
+        return self._list_paths(
+            self.path_info.bucket, prefix, progress_callback
+        )
 
     def _upload(
         self, from_file, to_info, name=None, no_progress_bar=False, **_kwargs

dvc/remote/config.py

@@ -1,157 +0,0 @@
-import logging
-import os
-import posixpath
-
-from dvc.config import Config
-from dvc.config import ConfigError
-from dvc.utils import relpath
-from dvc.utils.compat import urlparse
-
-
-logger = logging.getLogger(__name__)
-
-
-class RemoteConfig(object):
-    def __init__(self, config):
-        self.config = config
-
-    def get_settings(self, name):
-        """
-        Args:
-            name (str): The name of the remote that we want to retrieve
-
-        Returns:
-            dict: The content beneath the given remote name.
-
-        Example:
-            >>> config = {'remote "server"': {'url': 'ssh://localhost/'}}
-            >>> get_settings("server")
-            {'url': 'ssh://localhost/'}
-        """
-        settings = self.config.config.get(
-            Config.SECTION_REMOTE_FMT.format(name.lower())
-        )
-
-        if settings is None:
-            raise ConfigError(
-                "unable to find remote section '{}'".format(name)
-            )
-
-        parsed = urlparse(settings["url"])
-
-        # Support for cross referenced remotes.
-        # This will merge the settings, giving priority to the outer reference.
-        # For example, having:
-        #
-        #       dvc remote add server ssh://localhost
-        #       dvc remote modify server user root
-        #       dvc remote modify server ask_password true
-        #
-        #       dvc remote add images remote://server/tmp/pictures
-        #       dvc remote modify images user alice
-        #       dvc remote modify images ask_password false
-        #       dvc remote modify images password asdf1234
-        #
-        # Results on a config dictionary like:
-        #
-        #       {
-        #           "url": "ssh://localhost/tmp/pictures",
-        #           "user": "alice",
-        #           "password": "asdf1234",
-        #           "ask_password": False,
-        #       }
-        #
-        if parsed.scheme == "remote":
-            reference = self.get_settings(parsed.netloc)
-            url = posixpath.join(reference["url"], parsed.path.lstrip("/"))
-            merged = reference.copy()
-            merged.update(settings)
-            merged["url"] = url
-            return merged
-
-        return settings
-
-    @staticmethod
-    def resolve_path(path, config_file):
-        """Resolve path relative to config file location.
-
-        Args:
-            path: Path to be resolved.
-            config_file: Path to config file, which `path` is specified
-                relative to.
-
-        Returns:
-            Path relative to the `config_file` location. If `path` is an
-            absolute path then it will be returned without change.
-
-        """
-        if os.path.isabs(path):
-            return path
-        return relpath(path, os.path.dirname(config_file))
-
-    def add(self, name, url, default=False, force=False, level=None):
-        from dvc.remote import _get, RemoteLOCAL
-
-        configobj = self.config.get_configobj(level)
-        remote = _get({Config.SECTION_REMOTE_URL: url})
-        if remote == RemoteLOCAL and not url.startswith("remote://"):
-            url = self.resolve_path(url, configobj.filename)
-
-        self.config.set(
-            Config.SECTION_REMOTE_FMT.format(name),
-            Config.SECTION_REMOTE_URL,
-            url,
-            force=force,
-            level=level,
-        )
-        if default:
-            self.config.set(
-                Config.SECTION_CORE,
-                Config.SECTION_CORE_REMOTE,
-                name,
-                level=level,
-            )
-
-    def remove(self, name, level=None):
-        self.config.unset(Config.SECTION_REMOTE_FMT.format(name), level=level)
-
-        if level is None:
-            level = Config.LEVEL_REPO
-
-        for lev in [
-            Config.LEVEL_LOCAL,
-            Config.LEVEL_REPO,
-            Config.LEVEL_GLOBAL,
-            Config.LEVEL_SYSTEM,
-        ]:
-            self.config.unset(
-                Config.SECTION_CORE,
-                Config.SECTION_CORE_REMOTE,
-                level=lev,
-                force=True,
-            )
-            if lev == level:
-                break
-
-    def modify(self, name, option, value, level=None):
-        self.config.set(
-            Config.SECTION_REMOTE_FMT.format(name), option, value, level=level
-        )
-
-    def list(self, level=None):
-        return self.config.list_options(
-            Config.SECTION_REMOTE_REGEX, Config.SECTION_REMOTE_URL, level=level
-        )
-
-    def set_default(self, name, unset=False, level=None):
-        if unset:
-            self.config.unset(Config.SECTION_CORE, Config.SECTION_CORE_REMOTE)
-            return
-        self.config.set(
-            Config.SECTION_CORE, Config.SECTION_CORE_REMOTE, name, level=level
-        )
-
-    def get_default(self, level=None):
-        return self.config.get(
-            Config.SECTION_CORE, Config.SECTION_CORE_REMOTE, level=level
-        )

dvc/remote/gdrive.py

@@ -1,99 +1,363 @@
-from __future__ import unicode_literals
-
+import logging
 import os
 import posixpath
-import logging
+import re
 import threading
+from collections import defaultdict
+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.path_info import CloudURLInfo
-from dvc.remote.base import RemoteBASE
-from dvc.config import Config
 from dvc.exceptions import DvcException
-from dvc.utils import tmp_fname
+from dvc.path_info import CloudURLInfo
+from dvc.progress import Tqdm
+from dvc.remote.base import BaseRemote
+from dvc.scheme import Schemes
+from dvc.utils import format_link, tmp_fname
 
 logger = logging.getLogger(__name__)
 FOLDER_MIME_TYPE = "application/vnd.google-apps.folder"
 
 
-class GDriveRetriableError(DvcException):
-    def __init__(self, msg):
-        super(GDriveRetriableError, self).__init__(msg)
+class GDrivePathNotFound(DvcException):
+    def __init__(self, path_info, hint):
+        hint = "" if hint is None else f" {hint}"
+        super().__init__(f"GDrive path '{path_info}' not found.{hint}")
 
 
-@decorator
-def _wrap_pydrive_retriable(call):
-    from apiclient import errors
-    from pydrive.files import ApiRequestError
+class GDriveAuthError(DvcException):
+    def __init__(self, cred_location):
 
-    try:
-        result = call()
-    except (ApiRequestError, errors.HttpError) as exception:
-        retry_codes = ["403", "500", "502", "503", "504"]
-        if any(
-            "HttpError {}".format(code) in str(exception)
-            for code in retry_codes
-        ):
-            raise GDriveRetriableError(msg="Google API request failed")
-        raise
-    return result
+        if cred_location:
+            message = (
+                "GDrive remote auth failed with credentials in '{}'.\n"
+                "Backup first, remove of 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)
 
 
-gdrive_retry = compose(
-    # 8 tries, start at 0.5s, multiply by golden ratio, cap at 10s
-    retry(
-        8, GDriveRetriableError, timeout=lambda a: min(0.5 * 1.618 ** a, 10)
-    ),
-    _wrap_pydrive_retriable,
-)
+def _gdrive_retry(func):
+    def should_retry(exc):
+        from pydrive2.files import ApiRequestError
+
+        if not isinstance(exc, ApiRequestError):
+            return False
+
+        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}.")
+
+        return result
+
+    # 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 RemoteGDrive(RemoteBASE):
+class GDriveURLInfo(CloudURLInfo):
+    def __init__(self, url):
+        super().__init__(url)
+
+        # GDrive URL host part is case sensitive,
+        # we are restoring it here.
+        p = urlparse(url)
+        self.host = p.netloc
+        assert self.netloc == self.host
+
+        # Normalize path. Important since we have a cache (path to ID)
+        # and don't want to deal with different variations of path in it.
+        self._spath = re.sub("/{2,}", "/", self._spath.rstrip("/"))
+
+
+class GDriveRemote(BaseRemote):
     scheme = Schemes.GDRIVE
-    path_cls = CloudURLInfo
-    REQUIRES = {"pydrive": "pydrive"}
-    GDRIVE_USER_CREDENTIALS_DATA = "GDRIVE_USER_CREDENTIALS_DATA"
+    path_cls = GDriveURLInfo
+    REQUIRES = {"pydrive2": "pydrive2"}
+    DEFAULT_VERIFY = True
+    # Always prefer traverse for GDrive since API usage quotas are a concern.
+    TRAVERSE_WEIGHT_MULTIPLIER = 1
+    TRAVERSE_PREFIX_LEN = 2
+
+    GDRIVE_CREDENTIALS_DATA = "GDRIVE_CREDENTIALS_DATA"
     DEFAULT_USER_CREDENTIALS_FILE = "gdrive-user-credentials.json"
 
-    def __init__(self, repo, config):
-        super(RemoteGDrive, self).__init__(repo, config)
-        self.no_traverse = False
-        self.path_info = self.path_cls(config[Config.SECTION_REMOTE_URL])
-        self.config = config
-        self.init_drive()
+    DEFAULT_GDRIVE_CLIENT_ID = "710796635688-iivsgbgsb6uv1fap6635dhvuei09o66c.apps.googleusercontent.com"  # noqa: E501
+    DEFAULT_GDRIVE_CLIENT_SECRET = "a1Fz59uTpVNeG_VGuSKDLJXv"
 
-    def init_drive(self):
-        self.client_id = self.config.get(Config.SECTION_GDRIVE_CLIENT_ID, None)
-        self.client_secret = self.config.get(
-            Config.SECTION_GDRIVE_CLIENT_SECRET, None
-        )
-        if not self.client_id or not self.client_secret:
+    def __init__(self, repo, config):
+        super().__init__(repo, config)
+        self.path_info = self.path_cls(config["url"])
+
+        if not self.path_info.bucket:
             raise DvcException(
-                "Please specify Google Drive's client id and "
-                "secret in DVC's config. Learn more at "
-                "https://man.dvc.org/remote/add."
+                "Empty GDrive URL '{}'. Learn more at {}".format(
+                    config["url"],
+                    format_link("https://man.dvc.org/remote/add"),
+                )
             )
-        self.gdrive_user_credentials_path = (
-            tmp_fname(".dvc/tmp/")
-            if os.getenv(RemoteGDrive.GDRIVE_USER_CREDENTIALS_DATA)
-            else self.config.get(
-                Config.SECTION_GDRIVE_USER_CREDENTIALS_FILE,
+
+        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")
+        self._validate_config()
+        self._gdrive_user_credentials_path = (
+            tmp_fname(os.path.join(self.repo.tmp_dir, ""))
+            if os.getenv(GDriveRemote.GDRIVE_CREDENTIALS_DATA)
+            else config.get(
+                "gdrive_user_credentials_file",
                 os.path.join(
                     self.repo.tmp_dir, self.DEFAULT_USER_CREDENTIALS_FILE
                 ),
             )
         )
 
-    @gdrive_retry
-    def gdrive_upload_file(
-        self, args, no_progress_bar=True, from_file="", progress_name=""
+    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")
+                )
+            )
+
+        # 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")
+                    )
+                )
+
+    @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(GDriveRemote.GDRIVE_CREDENTIALS_DATA):
+            return GDriveRemote.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(GDriveRemote.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(GDriveRemote.GDRIVE_CREDENTIALS_DATA):
+            with open(self._gdrive_user_credentials_path, "w") as cred_file:
+                cred_file.write(
+                    os.getenv(GDriveRemote.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.update(auth_settings)
+
+        # 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()
+                GDriveRemote._validate_credentials(gauth, auth_settings)
+
+        # 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(GDriveRemote.GDRIVE_CREDENTIALS_DATA):
+                os.remove(self._gdrive_user_credentials_path)
+
+        return GoogleDrive(gauth)
+
+    @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.",
+            ),
+        }
+
+        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"])
+        ):
+            item_path = (self.path_info / item["title"]).path
+            self._cache_path_id(item_path, item["id"], cache)
+
+        return cache
+
+    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
+
+    @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"
+        return params
+
+    @_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=False,
+        from_file="",
+        progress_name="",
     ):
-        item = self.drive.CreateFile(
-            {"title": args["title"], "parents": [{"id": args["parent_id"]}]}
+        item = self._drive.CreateFile(
+            {"title": title, "parents": [{"id": parent_id}]}
         )
 
         with open(from_file, "rb") as fobj:
@@ -112,197 +376,188 @@ 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
     ):
-        gdrive_file = self.drive.CreateFile({"id": file_id})
-        bar_format = (
-            "Donwloading {desc:{ncols_desc}.{ncols_desc}}... "
-            + Tqdm.format_sizeof(int(gdrive_file["fileSize"]), "B", 1024)
-        )
+        param = {"id": item_id}
+        # it does not create a file on the remote
+        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):
-        file_list = self.drive.ListFile({"q": query, "maxResults": 1000})
+    @_gdrive_retry
+    def _gdrive_delete_file(self, item_id):
+        from pydrive2.files import ApiRequestError
 
-        # Isolate and decorate fetching of remote drive items in pages
-        get_list = gdrive_retry(lambda: next(file_list, None))
+        param = {"id": item_id}
+        # it does not create a file on the remote
+        item = self._drive.CreateFile(param)
 
-        # Fetch pages until None is received, lazily flatten the thing
+        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)
+        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))
+
+        # Fetch pages until None is received, lazily flatten the thing.
         return cat(iter(get_list, None))
 
-    def cache_root_dirs(self):
-        cached_dirs = {}
-        cached_ids = {}
-        for dir1 in self.gdrive_list_item(
-            "'{}' in parents and trashed=false".format(self.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"]
-        return cached_dirs, cached_ids
-
-    @property
-    def cached_dirs(self):
-        if not hasattr(self, "_cached_dirs"):
-            self.drive
-        return self._cached_dirs
-
-    @property
-    def cached_ids(self):
-        if not hasattr(self, "_cached_ids"):
-            self.drive
-        return self._cached_ids
-
-    @property
-    @wrap_with(threading.RLock())
-    def drive(self):
-        if not hasattr(self, "_gdrive"):
-            from pydrive.auth import GoogleAuth
-            from pydrive.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)
-                    )
-
-            GoogleAuth.DEFAULT_SETTINGS["client_config_backend"] = "settings"
-            GoogleAuth.DEFAULT_SETTINGS["client_config"] = {
-                "client_id": self.client_id,
-                "client_secret": self.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="")
-            gauth.CommandLineAuth()
-
-            if os.getenv(RemoteGDrive.GDRIVE_USER_CREDENTIALS_DATA):
-                os.remove(self.gdrive_user_credentials_path)
-
-            self._gdrive = GoogleDrive(gauth)
-
-            self.root_id = self.get_remote_id(self.path_info, create=True)
-            self._cached_dirs, self._cached_ids = self.cache_root_dirs()
-
-        return self._gdrive
-
-    @gdrive_retry
-    def create_remote_dir(self, parent_id, title):
-        item = self.drive.CreateFile(
-            {
-                "title": title,
-                "parents": [{"id": parent_id}],
-                "mimeType": FOLDER_MIME_TYPE,
-            }
+    @_gdrive_retry
+    def _gdrive_create_dir(self, parent_id, title):
+        parent = {"id": parent_id}
+        item = self._drive.CreateFile(
+            {"title": title, "parents": [parent], "mimeType": FOLDER_MIME_TYPE}
         )
         item.Upload()
         return item
 
-    @gdrive_retry
-    def get_remote_item(self, name, parents_ids):
-        if not parents_ids:
+    @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]
+
+        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 = " or ".join(
-            "'{}' in parents".format(parent_id) for parent_id in parents_ids
+        query = "trashed=false and ({})".format(
+            " or ".join(
+                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
+        ]
 
-        # Limit found remote items count to 1 in response
-        item_list = self.drive.ListFile(
-            {"q": query, "maxResults": 1}
-        ).GetList()
-        return next(iter(item_list), None)
-
-    def resolve_remote_item_from_path(self, path_parts, create):
-        parents_ids = ["root"]
-        current_path = ""
-        for path_part in path_parts:
-            current_path = posixpath.join(current_path, path_part)
-            remote_ids = self.get_remote_id_from_cache(current_path)
-            if remote_ids:
-                parents_ids = remote_ids
-                continue
-            item = self.get_remote_item(path_part, parents_ids)
-            if not item and create:
-                item = self.create_remote_dir(parents_ids[0], path_part)
-            elif not item:
-                return None
-            parents_ids = [item["id"]]
-        return item
-
-    def get_remote_id_from_cache(self, remote_path):
-        if hasattr(self, "_cached_dirs"):
-            return self.cached_dirs.get(remote_path, [])
+    def _get_cached_item_ids(self, path, use_cache):
+        if not path:
+            return [self._bucket]
+        if use_cache:
+            return self._ids_cache["dirs"].get(path, [])
         return []
 
-    def get_remote_id(self, path_info, create=False):
-        remote_ids = self.get_remote_id_from_cache(path_info.path)
+    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
 
-        if remote_ids:
-            return remote_ids[0]
+        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
 
-        file1 = self.resolve_remote_item_from_path(
-            path_info.path.split("/"), create
+        return (
+            [self._create_dir(min(parent_ids), title, path)] if create else []
         )
-        return file1["id"] if file1 else ""
+
+    def _get_item_id(self, path_info, create=False, use_cache=True, hint=None):
+        assert path_info.bucket == self._bucket
+
+        item_ids = self._path_to_item_ids(path_info.path, create, use_cache)
+        if item_ids:
+            return min(item_ids)
+
+        assert not create
+        raise GDrivePathNotFound(path_info, hint)
 
     def exists(self, path_info):
-        return self.get_remote_id(path_info) != ""
-
-    def _upload(self, from_file, to_info, name, no_progress_bar):
-        dirname = to_info.parent
-        if dirname:
-            parent_id = self.get_remote_id(dirname, True)
+        try:
+            self._get_item_id(path_info)
+        except GDrivePathNotFound:
+            return False
         else:
-            parent_id = to_info.bucket
+            return True
 
-        self.gdrive_upload_file(
-            {"title": to_info.name, "parent_id": parent_id},
-            no_progress_bar,
-            from_file,
-            name,
+    def _upload(self, from_file, to_info, name=None, no_progress_bar=False):
+        dirname = to_info.parent
+        assert dirname
+        parent_id = self._get_item_id(dirname, True)
+
+        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 _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)
 
-    def all(self):
-        if not self.cached_ids:
+    def list_cache_paths(self, prefix=None, progress_callback=None):
+        if not self._ids_cache["ids"]:
             return
 
-        query = " or ".join(
-            "'{}' in parents".format(dir_id) for dir_id in self.cached_ids
+        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"
 
-        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"')
+        for item in self._gdrive_list(query):
+            if progress_callback:
+                progress_callback()
+            parent_id = item["parents"][0]["id"]
+            yield posixpath.join(
+                self._ids_cache["ids"][parent_id], item["title"]
+            )
+
+    def remove(self, path_info):
+        item_id = self._get_item_id(path_info)
+        self._gdrive_delete_file(item_id)
+
+    def get_file_checksum(self, path_info):
+        raise NotImplementedError
+
+    def walk_files(self, path_info):
+        raise NotImplementedError

dvc/remote/gs.py

@@ -1,21 +1,17 @@
-from __future__ import unicode_literals, division
-
 import logging
+import os.path
+import posixpath
+import threading
 from datetime import timedelta
 from functools import wraps
-import io
-import os.path
-import threading
 
 from funcy import cached_property, wrap_prop
 
-from dvc.config import Config
 from dvc.exceptions import DvcException
 from dvc.path_info import CloudURLInfo
 from dvc.progress import Tqdm
-from dvc.remote.base import RemoteBASE
+from dvc.remote.base import BaseRemote
 from dvc.scheme import Schemes
-from dvc.utils.compat import FileNotFoundError  # skipcq: PYL-W0622
 
 logger = logging.getLogger(__name__)
 
@@ -55,10 +51,10 @@ def _upload_to_bucket(
     to_info,
     chunk_size=None,
     name=None,
-    no_progress_bar=True,
+    no_progress_bar=False,
 ):
     blob = bucket.blob(to_info.path, chunk_size=chunk_size)
-    with io.open(from_file, mode="rb") as fobj:
+    with open(from_file, mode="rb") as fobj:
         with Tqdm.wrapattr(
             fobj,
             "read",
@@ -69,20 +65,20 @@ def _upload_to_bucket(
             blob.upload_from_file(wrapped)
 
 
-class RemoteGS(RemoteBASE):
+class GSRemote(BaseRemote):
     scheme = Schemes.GS
     path_cls = CloudURLInfo
     REQUIRES = {"google-cloud-storage": "google.cloud.storage"}
     PARAM_CHECKSUM = "md5"
 
     def __init__(self, repo, config):
-        super(RemoteGS, self).__init__(repo, config)
+        super().__init__(repo, config)
 
-        url = config.get(Config.SECTION_REMOTE_URL, "gs:///")
+        url = config.get("url", "gs:///")
         self.path_info = self.path_cls(url)
 
-        self.projectname = config.get(Config.SECTION_GCP_PROJECTNAME, None)
-        self.credentialpath = config.get(Config.SECTION_GCP_CREDENTIALPATH)
+        self.projectname = config.get("projectname", None)
+        self.credentialpath = config.get("credentialpath")
 
     @wrap_prop(threading.Lock())
     @cached_property
@@ -113,7 +109,7 @@ class RemoteGS(RemoteBASE):
         from_bucket = self.gs.bucket(from_info.bucket)
         blob = from_bucket.get_blob(from_info.path)
         if not blob:
-            msg = "'{}' doesn't exist in the cloud".format(from_info.path)
+            msg = f"'{from_info.path}' doesn't exist in the cloud"
             raise DvcException(msg)
 
         to_bucket = self.gs.bucket(to_info.bucket)
@@ -123,21 +119,31 @@ class RemoteGS(RemoteBASE):
         if path_info.scheme != "gs":
             raise NotImplementedError
 
-        logger.debug("Removing gs://{}".format(path_info))
+        logger.debug(f"Removing gs://{path_info}")
         blob = self.gs.bucket(path_info.bucket).get_blob(path_info.path)
         if not blob:
             return
 
         blob.delete()
 
-    def _list_paths(self, path_info, max_items=None):
+    def _list_paths(
+        self, path_info, max_items=None, prefix=None, progress_callback=None
+    ):
+        if prefix:
+            prefix = posixpath.join(path_info.path, prefix[:2], prefix[2:])
+        else:
+            prefix = path_info.path
         for blob in self.gs.bucket(path_info.bucket).list_blobs(
             prefix=path_info.path, max_results=max_items
         ):
+            if progress_callback:
+                progress_callback()
             yield blob.name
 
-    def list_cache_paths(self):
-        return self._list_paths(self.path_info)
+    def list_cache_paths(self, prefix=None, progress_callback=None):
+        return self._list_paths(
+            self.path_info, prefix=prefix, progress_callback=progress_callback
+        )
 
     def walk_files(self, path_info):
         for fname in self._list_paths(path_info / ""):
@@ -147,6 +153,9 @@ class RemoteGS(RemoteBASE):
             yield path_info.replace(fname)
 
     def makedirs(self, path_info):
+        if not path_info.path:
+            return
+
         self.gs.bucket(path_info.bucket).blob(
             (path_info / "").path
         ).upload_from_string("")
@@ -170,7 +179,7 @@ class RemoteGS(RemoteBASE):
         """
         return self.isfile(path_info) or self.isdir(path_info)
 
-    def _upload(self, from_file, to_info, name=None, no_progress_bar=True):
+    def _upload(self, from_file, to_info, name=None, no_progress_bar=False):
         bucket = self.gs.bucket(to_info.bucket)
         _upload_to_bucket(
             bucket,
@@ -180,10 +189,10 @@ class RemoteGS(RemoteBASE):
             no_progress_bar=no_progress_bar,
         )
 
-    def _download(self, from_info, to_file, name=None, no_progress_bar=True):
+    def _download(self, from_info, to_file, name=None, no_progress_bar=False):
         bucket = self.gs.bucket(from_info.bucket)
         blob = bucket.get_blob(from_info.path)
-        with io.open(to_file, mode="wb") as fobj:
+        with open(to_file, mode="wb") as fobj:
             with Tqdm.wrapattr(
                 fobj,
                 "write",

dvc/remote/hdfs.py

@@ -1,40 +1,38 @@
-from __future__ import unicode_literals
-
-from dvc.utils.compat import FileNotFoundError, urlparse
 import io
 import logging
 import os
 import posixpath
 import re
+import subprocess
 from collections import deque
 from contextlib import closing, contextmanager
-import subprocess
+from urllib.parse import urlparse
 
-from .base import RemoteBASE, RemoteCmdError
-from .pool import get_connection
-from dvc.config import Config
 from dvc.scheme import Schemes
 from dvc.utils import fix_env, tmp_fname
 
+from .base import BaseRemote, RemoteCmdError
+from .pool import get_connection
+
 logger = logging.getLogger(__name__)
 
 
-class RemoteHDFS(RemoteBASE):
+class HDFSRemote(BaseRemote):
     scheme = Schemes.HDFS
     REGEX = r"^hdfs://((?P<user>.*)@)?.*$"
     PARAM_CHECKSUM = "checksum"
     REQUIRES = {"pyarrow": "pyarrow"}
+    TRAVERSE_PREFIX_LEN = 2
 
     def __init__(self, repo, config):
-        super(RemoteHDFS, self).__init__(repo, config)
+        super().__init__(repo, config)
         self.path_info = None
-        url = config.get(Config.SECTION_REMOTE_URL)
+        url = config.get("url")
         if not url:
             return
 
         parsed = urlparse(url)
-
-        user = parsed.username or config.get(Config.SECTION_REMOTE_USER)
+        user = parsed.username or config.get("user")
 
         self.path_info = self.path_cls.from_parts(
             scheme=self.scheme,
@@ -57,7 +55,7 @@ class RemoteHDFS(RemoteBASE):
     def hadoop_fs(self, cmd, user=None):
         cmd = "hadoop fs -" + cmd
         if user:
-            cmd = "HADOOP_USER_NAME={} ".format(user) + cmd
+            cmd = f"HADOOP_USER_NAME={user} " + cmd
 
         # NOTE: close_fds doesn't work with redirected stdin/stdout/stderr.
         # See https://github.com/iterative/dvc/issues/1197.
@@ -89,7 +87,7 @@ class RemoteHDFS(RemoteBASE):
         # NOTE: pyarrow doesn't support checksum, so we need to use hadoop
         regex = r".*\t.*\t(?P<checksum>.*)"
         stdout = self.hadoop_fs(
-            "checksum {}".format(path_info.path), user=path_info.user
+            f"checksum {path_info.path}", user=path_info.user
         )
         return self._group(regex, stdout, "checksum")
 
@@ -114,7 +112,7 @@ class RemoteHDFS(RemoteBASE):
             raise NotImplementedError
 
         if self.exists(path_info):
-            logger.debug("Removing {}".format(path_info.path))
+            logger.debug(f"Removing {path_info.path}")
             with self.hdfs(path_info) as hdfs:
                 hdfs.rm(path_info.path)
 
@@ -149,23 +147,36 @@ class RemoteHDFS(RemoteBASE):
                     yield fd
                 else:
                     yield io.TextIOWrapper(fd, encoding=encoding)
-        except IOError as e:
+        except OSError as e:
             # Empty .errno and not specific enough error class in pyarrow,
             # see https://issues.apache.org/jira/browse/ARROW-6248
             if "file does not exist" in str(e):
                 raise FileNotFoundError(*e.args)
             raise
 
-    def list_cache_paths(self):
+    def list_cache_paths(self, prefix=None, progress_callback=None):
         if not self.exists(self.path_info):
             return
 
-        dirs = deque([self.path_info.path])
+        if prefix:
+            root = posixpath.join(self.path_info.path, prefix[:2])
+        else:
+            root = self.path_info.path
+        dirs = deque([root])
 
         with self.hdfs(self.path_info) as hdfs:
             while dirs:
-                for entry in hdfs.ls(dirs.pop(), detail=True):
-                    if entry["kind"] == "directory":
-                        dirs.append(urlparse(entry["name"]).path)
-                    elif entry["kind"] == "file":
-                        yield urlparse(entry["name"]).path
+                try:
+                    entries = hdfs.ls(dirs.pop(), detail=True)
+                    for entry in entries:
+                        if entry["kind"] == "directory":
+                            dirs.append(urlparse(entry["name"]).path)
+                        elif entry["kind"] == "file":
+                            if progress_callback:
+                                progress_callback()
+                            yield urlparse(entry["name"]).path
+                except OSError as e:
+                    # When searching for a specific prefix pyarrow raises an
+                    # exception if the specified cache dir does not exist
+                    if not prefix:
+                        raise e

dvc/remote/http.py

@@ -1,56 +1,96 @@
-from __future__ import unicode_literals
-
 import logging
+import os.path
 import threading
 
-from funcy import cached_property, wrap_prop
+from funcy import cached_property, memoize, wrap_prop, wrap_with
 
-from dvc.config import Config
-from dvc.config import ConfigError
+import dvc.prompt as prompt
 from dvc.exceptions import DvcException, HTTPError
+from dvc.path_info import HTTPURLInfo
 from dvc.progress import Tqdm
-from dvc.remote.base import RemoteBASE
+from dvc.remote.base import BaseRemote
 from dvc.scheme import Schemes
-from dvc.utils.compat import open
 
 logger = logging.getLogger(__name__)
 
 
-class RemoteHTTP(RemoteBASE):
+@wrap_with(threading.Lock())
+@memoize
+def ask_password(host, user):
+    return prompt.password(
+        "Enter a password for "
+        "host '{host}' user '{user}'".format(host=host, user=user)
+    )
+
+
+class HTTPRemote(BaseRemote):
     scheme = Schemes.HTTP
+    path_cls = HTTPURLInfo
     SESSION_RETRIES = 5
     SESSION_BACKOFF_FACTOR = 0.1
     REQUEST_TIMEOUT = 10
     CHUNK_SIZE = 2 ** 16
     PARAM_CHECKSUM = "etag"
+    CAN_TRAVERSE = False
 
     def __init__(self, repo, config):
-        super(RemoteHTTP, self).__init__(repo, config)
+        super().__init__(repo, config)
 
-        url = config.get(Config.SECTION_REMOTE_URL)
-        self.path_info = self.path_cls(url) if url else None
+        url = config.get("url")
+        if url:
+            self.path_info = self.path_cls(url)
+            user = config.get("user", None)
+            if user:
+                self.path_info.user = user
+        else:
+            self.path_info = None
 
-        if not self.no_traverse:
-            raise ConfigError(
-                "HTTP doesn't support traversing the remote to list existing "
-                "files. Use: `dvc remote modify <name> no_traverse true`"
-            )
+        self.auth = config.get("auth", None)
+        self.custom_auth_header = config.get("custom_auth_header", None)
+        self.password = config.get("password", None)
+        self.ask_password = config.get("ask_password", False)
+        self.headers = {}
 
     def _download(self, from_info, to_file, name=None, no_progress_bar=False):
         response = self._request("GET", from_info.url, stream=True)
         if response.status_code != 200:
             raise HTTPError(response.status_code, response.reason)
-        with Tqdm(
-            total=None if no_progress_bar else self._content_length(response),
-            leave=False,
-            bytes=True,
-            desc=from_info.url if name is None else name,
-            disable=no_progress_bar,
-        ) as pbar:
-            with open(to_file, "wb") as fd:
+        with open(to_file, "wb") as fd:
+            with Tqdm.wrapattr(
+                fd,
+                "write",
+                total=None
+                if no_progress_bar
+                else self._content_length(response),
+                leave=False,
+                desc=from_info.url if name is None else name,
+                disable=no_progress_bar,
+            ) as fd_wrapped:
                 for chunk in response.iter_content(chunk_size=self.CHUNK_SIZE):
-                    fd.write(chunk)
-                    pbar.update(len(chunk))
+                    fd_wrapped.write(chunk)
+
+    def _upload(self, from_file, to_info, name=None, no_progress_bar=False):
+        def chunks():
+            with open(from_file, "rb") as fd:
+                with Tqdm.wrapattr(
+                    fd,
+                    "read",
+                    total=None
+                    if no_progress_bar
+                    else os.path.getsize(from_file),
+                    leave=False,
+                    desc=to_info.url if name is None else name,
+                    disable=no_progress_bar,
+                ) as fd_wrapped:
+                    while True:
+                        chunk = fd_wrapped.read(self.CHUNK_SIZE)
+                        if not chunk:
+                            break
+                        yield chunk
+
+        response = self._request("POST", to_info.url, data=chunks())
+        if response.status_code not in (200, 201):
+            raise HTTPError(response.status_code, response.reason)
 
     def exists(self, path_info):
         return bool(self._request("HEAD", path_info.url))
@@ -78,6 +118,24 @@ class RemoteHTTP(RemoteBASE):
 
         return etag
 
+    def auth_method(self, path_info=None):
+        from requests.auth import HTTPBasicAuth, HTTPDigestAuth
+
+        if path_info is None:
+            path_info = self.path_info
+
+        if self.auth:
+            if self.ask_password and self.password is None:
+                host, user = path_info.host, path_info.user
+                self.password = ask_password(host, user)
+            if self.auth == "basic":
+                return HTTPBasicAuth(path_info.user, self.password)
+            if self.auth == "digest":
+                return HTTPDigestAuth(path_info.user, self.password)
+            if self.auth == "custom" and self.custom_auth_header:
+                self.headers.update({self.custom_auth_header: self.password})
+        return None
+
     @wrap_prop(threading.Lock())
     @cached_property
     def _session(self):
@@ -104,9 +162,30 @@ class RemoteHTTP(RemoteBASE):
         kwargs.setdefault("timeout", self.REQUEST_TIMEOUT)
 
         try:
-            return self._session.request(method, url, **kwargs)
+            res = self._session.request(
+                method,
+                url,
+                auth=self.auth_method(),
+                headers=self.headers,
+                **kwargs,
+            )
+
+            redirect_no_location = (
+                kwargs["allow_redirects"]
+                and res.status_code in (301, 302)
+                and "location" not in res.headers
+            )
+
+            if redirect_no_location:
+                # AWS s3 doesn't like to add a location header to its redirects
+                # from https://s3.amazonaws.com/<bucket name>/* type URLs.
+                # This should be treated as an error
+                raise requests.exceptions.RequestException
+
+            return res
+
         except requests.exceptions.RequestException:
-            raise DvcException("could not perform a {} request".format(method))
+            raise DvcException(f"could not perform a {method} request")
 
     def gc(self):
         raise NotImplementedError

dvc/remote/https.py

@@ -1,8 +1,7 @@
-from __future__ import unicode_literals
-
-from .http import RemoteHTTP
 from dvc.scheme import Schemes
 
+from .http import HTTPRemote
 
-class RemoteHTTPS(RemoteHTTP):
+
+class HTTPSRemote(HTTPRemote):
     scheme = Schemes.HTTPS

dvc/remote/index.py

@@ -0,0 +1,212 @@
+import logging
+import os
+import sqlite3
+import threading
+
+from funcy import lchunks
+
+from dvc.state import _connect_sqlite
+
+logger = logging.getLogger(__name__)
+
+
+class RemoteIndexNoop:
+    """No-op class for remotes which are not indexed (i.e. local)."""
+
+    def __init__(self, *args, **kwargs):
+        pass
+
+    def __enter__(self):
+        pass
+
+    def __exit__(self, typ, value, tbck):
+        pass
+
+    def __iter__(self):
+        return iter([])
+
+    def __contains__(self, checksum):
+        return False
+
+    @staticmethod
+    def checksums():
+        return []
+
+    @staticmethod
+    def dir_checksums():
+        return []
+
+    def load(self):
+        pass
+
+    def dump(self):
+        pass
+
+    def clear(self):
+        pass
+
+    def update(self, *args):
+        pass
+
+    @staticmethod
+    def intersection(*args):
+        return []
+
+
+class RemoteIndex:
+    """Class for indexing remote checksums in a sqlite3 database.
+
+    Args:
+        repo: repo for this remote index.
+        name: name for this index. Index db will be loaded from and saved to
+            ``.dvc/tmp/index/{name}.idx``.
+        dir_suffix: suffix used for naming directory checksums
+    """
+
+    INDEX_SUFFIX = ".idx"
+    VERSION = 1
+    INDEX_TABLE = "remote_index"
+    INDEX_TABLE_LAYOUT = "checksum TEXT PRIMARY KEY, " "dir INTEGER NOT NULL"
+
+    def __init__(self, repo, name, dir_suffix=".dir"):
+        self.path = os.path.join(repo.index_dir, f"{name}{self.INDEX_SUFFIX}")
+
+        self.dir_suffix = dir_suffix
+        self.database = None
+        self.cursor = None
+        self.modified = False
+        self.lock = threading.Lock()
+
+    def __iter__(self):
+        cmd = f"SELECT checksum FROM {self.INDEX_TABLE}"
+        for (checksum,) in self._execute(cmd):
+            yield checksum
+
+    def __enter__(self):
+        self.lock.acquire()
+        self.load()
+
+    def __exit__(self, typ, value, tbck):
+        self.dump()
+        self.lock.release()
+
+    def __contains__(self, checksum):
+        cmd = "SELECT checksum FROM {} WHERE checksum = (?)".format(
+            self.INDEX_TABLE
+        )
+        self._execute(cmd, (checksum,))
+        return self.cursor.fetchone() is not None
+
+    def checksums(self):
+        """Iterate over checksums stored in the index."""
+        return iter(self)
+
+    def dir_checksums(self):
+        """Iterate over .dir checksums stored in the index."""
+        cmd = f"SELECT checksum FROM {self.INDEX_TABLE} WHERE dir = 1"
+        for (checksum,) in self._execute(cmd):
+            yield checksum
+
+    def is_dir_checksum(self, checksum):
+        return checksum.endswith(self.dir_suffix)
+
+    def _execute(self, cmd, parameters=()):
+        return self.cursor.execute(cmd, parameters)
+
+    def _executemany(self, cmd, seq_of_parameters):
+        return self.cursor.executemany(cmd, seq_of_parameters)
+
+    def _prepare_db(self, empty=False):
+        if not empty:
+            cmd = "PRAGMA user_version;"
+            self._execute(cmd)
+            ret = self.cursor.fetchall()
+            assert len(ret) == 1
+            assert len(ret[0]) == 1
+            assert isinstance(ret[0][0], int)
+            version = ret[0][0]
+
+            if version != self.VERSION:
+                logger.error(
+                    "Index file version '{}' will be reformatted "
+                    "to the current version '{}'.".format(
+                        version, self.VERSION,
+                    )
+                )
+                cmd = "DROP TABLE IF EXISTS {};"
+                self._execute(cmd.format(self.INDEX_TABLE))
+
+        cmd = "CREATE TABLE IF NOT EXISTS {} ({})"
+        self._execute(cmd.format(self.INDEX_TABLE, self.INDEX_TABLE_LAYOUT))
+
+        cmd = "PRAGMA user_version = {};"
+        self._execute(cmd.format(self.VERSION))
+
+    def load(self):
+        """(Re)load this index database."""
+        retries = 1
+        while True:
+            assert self.database is None
+            assert self.cursor is None
+
+            empty = not os.path.isfile(self.path)
+            self.database = _connect_sqlite(self.path, {"nolock": 1})
+            self.cursor = self.database.cursor()
+
+            try:
+                self._prepare_db(empty=empty)
+                return
+            except sqlite3.DatabaseError:
+                self.cursor.close()
+                self.database.close()
+                self.database = None
+                self.cursor = None
+                if retries > 0:
+                    os.unlink(self.path)
+                    retries -= 1
+                else:
+                    raise
+
+    def dump(self):
+        """Save this index database."""
+        assert self.database is not None
+
+        self.database.commit()
+        self.cursor.close()
+        self.database.close()
+        self.database = None
+        self.cursor = None
+
+    def clear(self):
+        """Clear this index (to force re-indexing later).
+
+        Changes to the index will not committed until dump() is called.
+        """
+        cmd = f"DELETE FROM {self.INDEX_TABLE}"
+        self._execute(cmd)
+
+    def update(self, dir_checksums, file_checksums):
+        """Update this index, adding the specified checksums.
+
+        Changes to the index will not committed until dump() is called.
+        """
+        cmd = "INSERT OR IGNORE INTO {} (checksum, dir) VALUES (?, ?)".format(
+            self.INDEX_TABLE
+        )
+        self._executemany(
+            cmd, ((checksum, True) for checksum in dir_checksums)
+        )
+        self._executemany(
+            cmd, ((checksum, False) for checksum in file_checksums)
+        )
+
+    def intersection(self, checksums):
+        """Iterate over values from `checksums` which exist in the index."""
+        # sqlite has a compile time limit of 999, see:
+        # https://www.sqlite.org/c3ref/c_limit_attached.html#sqlitelimitvariablenumber
+        for chunk in lchunks(999, checksums):
+            cmd = "SELECT checksum FROM {} WHERE checksum IN ({})".format(
+                self.INDEX_TABLE, ",".join("?" for checksum in chunk)
+            )
+            for (checksum,) in self._execute(cmd, chunk):
+                yield checksum

dvc/remote/local.py

@@ -1,72 +1,52 @@
-from __future__ import unicode_literals
-
 import errno
 import logging
 import os
 import stat
-from concurrent.futures import ThreadPoolExecutor
+from concurrent.futures import ThreadPoolExecutor, as_completed
 from functools import partial
 
+from funcy import cached_property, concat
 from shortuuid import uuid
 
-from dvc.config import Config
-from dvc.exceptions import DownloadError
-from dvc.exceptions import DvcException
-from dvc.exceptions import UploadError
+from dvc.exceptions import DownloadError, DvcException, UploadError
 from dvc.path_info import PathInfo
 from dvc.progress import Tqdm
-from dvc.remote.base import RemoteBASE
-from dvc.remote.base import STATUS_DELETED
-from dvc.remote.base import STATUS_MAP
-from dvc.remote.base import STATUS_MISSING
-from dvc.remote.base import STATUS_NEW
+from dvc.remote.base import (
+    STATUS_DELETED,
+    STATUS_MAP,
+    STATUS_MISSING,
+    STATUS_NEW,
+    BaseRemote,
+    index_locked,
+)
+from dvc.remote.index import RemoteIndexNoop
 from dvc.scheme import Schemes
+from dvc.scm.tree import is_working_tree
 from dvc.system import System
-from dvc.utils import copyfile
-from dvc.utils import file_md5
-from dvc.utils import makedirs
-from dvc.utils import relpath
-from dvc.utils import tmp_fname
-from dvc.utils import walk_files
-from dvc.utils.compat import fspath_py35
-from dvc.utils.compat import open
-from dvc.utils.compat import str
-from dvc.utils.fs import move
-from dvc.utils.fs import remove
+from dvc.utils import file_md5, relpath, tmp_fname
+from dvc.utils.fs import copyfile, makedirs, move, remove, walk_files
 
 logger = logging.getLogger(__name__)
 
 
-class RemoteLOCAL(RemoteBASE):
+class LocalRemote(BaseRemote):
     scheme = Schemes.LOCAL
     path_cls = PathInfo
     PARAM_CHECKSUM = "md5"
     PARAM_PATH = "path"
+    TRAVERSE_PREFIX_LEN = 2
+    INDEX_CLS = RemoteIndexNoop
 
     UNPACKED_DIR_SUFFIX = ".unpacked"
 
     DEFAULT_CACHE_TYPES = ["reflink", "copy"]
 
+    CACHE_MODE = 0o444
     SHARED_MODE_MAP = {None: (0o644, 0o755), "group": (0o664, 0o775)}
 
     def __init__(self, repo, config):
-        super(RemoteLOCAL, self).__init__(repo, config)
-        self.protected = config.get(Config.SECTION_CACHE_PROTECTED, False)
-
-        shared = config.get(Config.SECTION_CACHE_SHARED)
-        self._file_mode, self._dir_mode = self.SHARED_MODE_MAP[shared]
-
-        if self.protected:
-            # cache files are set to be read-only for everyone
-            self._file_mode = stat.S_IREAD | stat.S_IRGRP | stat.S_IROTH
-
-        cache_dir = config.get(Config.SECTION_REMOTE_URL)
-
-        if cache_dir is not None and not os.path.isabs(cache_dir):
-            cwd = config[Config.PRIVATE_CWD]
-            cache_dir = os.path.abspath(os.path.join(cwd, cache_dir))
-
-        self.path_info = PathInfo(cache_dir) if cache_dir else None
+        super().__init__(repo, config)
+        self.cache_dir = config.get("url")
         self._dir_info = {}
 
     @property
@@ -77,13 +57,33 @@ class RemoteLOCAL(RemoteBASE):
     def cache_dir(self):
         return self.path_info.fspath if self.path_info else None
 
+    @cache_dir.setter
+    def cache_dir(self, value):
+        self.path_info = PathInfo(value) if value else None
+
     @classmethod
     def supported(cls, config):
         return True
 
-    def list_cache_paths(self):
+    @cached_property
+    def cache_path(self):
+        return os.path.abspath(self.cache_dir)
+
+    def checksum_to_path(self, checksum):
+        return os.path.join(self.cache_path, checksum[0:2], checksum[2:])
+
+    def list_cache_paths(self, prefix=None, progress_callback=None):
         assert self.path_info is not None
-        return walk_files(self.path_info, None)
+        if prefix:
+            path_info = self.path_info / prefix[:2]
+        else:
+            path_info = self.path_info
+        if progress_callback:
+            for path in walk_files(path_info):
+                progress_callback()
+                yield path
+        else:
+            yield from walk_files(path_info)
 
     def get(self, md5):
         if not md5:
@@ -91,10 +91,10 @@ class RemoteLOCAL(RemoteBASE):
 
         return self.checksum_to_path_info(md5).url
 
-    @staticmethod
-    def exists(path_info):
-        assert path_info.scheme == "local"
-        return os.path.lexists(fspath_py35(path_info))
+    def exists(self, path_info):
+        assert is_working_tree(self.repo.tree)
+        assert isinstance(path_info, str) or path_info.scheme == "local"
+        return self.repo.tree.exists(path_info)
 
     def makedirs(self, path_info):
         makedirs(path_info, exist_ok=True, mode=self._dir_mode)
@@ -109,6 +109,12 @@ class RemoteLOCAL(RemoteBASE):
 
         return not self.changed_cache(current_md5)
 
+    def _verify_link(self, path_info, link_type):
+        if link_type == "hardlink" and self.getsize(path_info) == 0:
+            return
+
+        super()._verify_link(path_info, link_type)
+
     def is_empty(self, path_info):
         path = path_info.fspath
 
@@ -122,11 +128,11 @@ class RemoteLOCAL(RemoteBASE):
 
     @staticmethod
     def isfile(path_info):
-        return os.path.isfile(fspath_py35(path_info))
+        return os.path.isfile(path_info)
 
     @staticmethod
     def isdir(path_info):
-        return os.path.isdir(fspath_py35(path_info))
+        return os.path.isdir(path_info)
 
     def iscopy(self, path_info):
         return not (
@@ -135,32 +141,39 @@ class RemoteLOCAL(RemoteBASE):
 
     @staticmethod
     def getsize(path_info):
-        return os.path.getsize(fspath_py35(path_info))
+        return os.path.getsize(path_info)
 
     def walk_files(self, path_info):
-        for fname in walk_files(path_info, self.repo.dvcignore):
+        assert is_working_tree(self.repo.tree)
+
+        for fname in self.repo.tree.walk_files(path_info):
             yield PathInfo(fname)
 
     def get_file_checksum(self, path_info):
         return file_md5(path_info)[0]
 
     def remove(self, path_info):
-        if path_info.scheme != "local":
-            raise NotImplementedError
+        if isinstance(path_info, PathInfo):
+            if path_info.scheme != "local":
+                raise NotImplementedError
+            path = path_info.fspath
+        else:
+            path = path_info
 
-        if self.exists(path_info):
-            remove(path_info.fspath)
+        if self.exists(path):
+            remove(path)
 
-    def move(self, from_info, to_info):
+    def move(self, from_info, to_info, mode=None):
         if from_info.scheme != "local" or to_info.scheme != "local":
             raise NotImplementedError
 
         self.makedirs(to_info.parent)
 
-        if self.isfile(from_info):
-            mode = self._file_mode
-        else:
-            mode = self._dir_mode
+        if mode is None:
+            if self.isfile(from_info):
+                mode = self._file_mode
+            else:
+                mode = self._dir_mode
 
         move(from_info, to_info, mode=mode)
 
@@ -168,7 +181,8 @@ class RemoteLOCAL(RemoteBASE):
         tmp_info = to_info.parent / tmp_fname(to_info.name)
         try:
             System.copy(from_info, tmp_info)
-            os.rename(fspath_py35(tmp_info), fspath_py35(to_info))
+            os.chmod(tmp_info, self._file_mode)
+            os.rename(tmp_info, to_info)
         except Exception:
             self.remove(tmp_info)
             raise
@@ -177,6 +191,10 @@ class RemoteLOCAL(RemoteBASE):
     def symlink(from_info, to_info):
         System.symlink(from_info, to_info)
 
+    @staticmethod
+    def is_symlink(path_info):
+        return System.is_symlink(path_info)
+
     def hardlink(self, from_info, to_info):
         # If there are a lot of empty files (which happens a lot in datasets),
         # and the cache type is `hardlink`, we might reach link limits and
@@ -204,8 +222,16 @@ class RemoteLOCAL(RemoteBASE):
         System.hardlink(from_info, to_info)
 
     @staticmethod
-    def reflink(from_info, to_info):
-        System.reflink(from_info, to_info)
+    def is_hardlink(path_info):
+        return System.is_hardlink(path_info)
+
+    def reflink(self, from_info, to_info):
+        tmp_info = to_info.parent / tmp_fname(to_info.name)
+        System.reflink(from_info, tmp_info)
+        # NOTE: reflink has its own separate inode, so you can set permissions
+        # that are different from the source.
+        os.chmod(tmp_info, self._file_mode)
+        os.rename(tmp_info, to_info)
 
     def cache_exists(self, checksums, jobs=None, name=None):
         return [
@@ -228,7 +254,7 @@ class RemoteLOCAL(RemoteBASE):
         copyfile(
             from_file, tmp_file, name=name, no_progress_bar=no_progress_bar
         )
-        os.rename(tmp_file, fspath_py35(to_info))
+        os.rename(tmp_file, to_info)
 
     def _download(
         self, from_info, to_file, name=None, no_progress_bar=False, **_kwargs
@@ -239,8 +265,9 @@ class RemoteLOCAL(RemoteBASE):
 
     @staticmethod
     def open(path_info, mode="r", encoding=None):
-        return open(fspath_py35(path_info), mode=mode, encoding=encoding)
+        return open(path_info, mode=mode, encoding=encoding)
 
+    @index_locked
     def status(
         self,
         named_cache,
@@ -249,37 +276,128 @@ class RemoteLOCAL(RemoteBASE):
         show_checksums=False,
         download=False,
     ):
-        logger.debug(
-            "Preparing to collect status from {}".format(remote.path_info)
+        # Return flattened dict containing all status info
+        dir_status, file_status, _ = self._status(
+            named_cache,
+            remote,
+            jobs=jobs,
+            show_checksums=show_checksums,
+            download=download,
         )
-        md5s = list(named_cache[self.scheme])
+        return dict(dir_status, **file_status)
+
+    def _status(
+        self,
+        named_cache,
+        remote,
+        jobs=None,
+        show_checksums=False,
+        download=False,
+    ):
+        """Return a tuple of (dir_status_info, file_status_info, dir_contents).
+
+        dir_status_info contains status for .dir files, file_status_info
+        contains status for all other files, and dir_contents is a dict of
+        {dir_checksum: set(file_checksum, ...)} which can be used to map
+        a .dir file to its file contents.
+        """
+        logger.debug(f"Preparing to collect status from {remote.path_info}")
+        md5s = set(named_cache.scheme_keys(self.scheme))
 
         logger.debug("Collecting information from local cache...")
-        local_exists = self.cache_exists(md5s, jobs=jobs, name=self.cache_dir)
+        local_exists = frozenset(
+            self.cache_exists(md5s, jobs=jobs, name=self.cache_dir)
+        )
 
         # This is a performance optimization. We can safely assume that,
         # if the resources that we want to fetch are already cached,
         # there's no need to check the remote storage for the existence of
         # those files.
-        if download and sorted(local_exists) == sorted(md5s):
+        if download and local_exists == md5s:
             remote_exists = local_exists
         else:
             logger.debug("Collecting information from remote cache...")
-            remote_exists = list(
-                remote.cache_exists(
-                    md5s, jobs=jobs, name=str(remote.path_info)
+            remote_exists = set()
+            dir_md5s = set(named_cache.dir_keys(self.scheme))
+            if dir_md5s:
+                remote_exists.update(
+                    self._indexed_dir_checksums(named_cache, remote, dir_md5s)
                 )
+                md5s.difference_update(remote_exists)
+            if md5s:
+                remote_exists.update(
+                    remote.cache_exists(
+                        md5s, jobs=jobs, name=str(remote.path_info)
+                    )
+                )
+        return self._make_status(
+            named_cache, show_checksums, local_exists, remote_exists
+        )
+
+    def _make_status(
+        self, named_cache, show_checksums, local_exists, remote_exists
+    ):
+        def make_names(checksum, names):
+            return {"name": checksum if show_checksums else " ".join(names)}
+
+        dir_status = {}
+        file_status = {}
+        dir_contents = {}
+        for checksum, item in named_cache[self.scheme].items():
+            if item.children:
+                dir_status[checksum] = make_names(checksum, item.names)
+                dir_contents[checksum] = set()
+                for child_checksum, child in item.children.items():
+                    file_status[child_checksum] = make_names(
+                        child_checksum, child.names
+                    )
+                    dir_contents[checksum].add(child_checksum)
+            else:
+                file_status[checksum] = make_names(checksum, item.names)
+
+        self._fill_statuses(dir_status, local_exists, remote_exists)
+        self._fill_statuses(file_status, local_exists, remote_exists)
+
+        self._log_missing_caches(dict(dir_status, **file_status))
+
+        return dir_status, file_status, dir_contents
+
+    def _indexed_dir_checksums(self, named_cache, remote, dir_md5s):
+        # Validate our index by verifying all indexed .dir checksums
+        # still exist on the remote
+        indexed_dirs = set(remote.index.dir_checksums())
+        indexed_dir_exists = set()
+        if indexed_dirs:
+            indexed_dir_exists.update(
+                remote._cache_object_exists(indexed_dirs)
             )
+            missing_dirs = indexed_dirs.difference(indexed_dir_exists)
+            if missing_dirs:
+                logger.debug(
+                    "Remote cache missing indexed .dir checksums '{}', "
+                    "clearing remote index".format(", ".join(missing_dirs))
+                )
+                remote.index.clear()
 
-        ret = {
-            checksum: {"name": checksum if show_checksums else " ".join(names)}
-            for checksum, names in named_cache[self.scheme].items()
-        }
-        self._fill_statuses(ret, local_exists, remote_exists)
+        # Check if non-indexed (new) dir checksums exist on remote
+        dir_exists = dir_md5s.intersection(indexed_dir_exists)
+        dir_exists.update(remote._cache_object_exists(dir_md5s - dir_exists))
 
-        self._log_missing_caches(ret)
-
-        return ret
+        # If .dir checksum exists on the remote, assume directory contents
+        # still exists on the remote
+        for dir_checksum in dir_exists:
+            file_checksums = list(
+                named_cache.child_keys(self.scheme, dir_checksum)
+            )
+            if dir_checksum not in remote.index:
+                logger.debug(
+                    "Indexing new .dir '{}' with '{}' nested files".format(
+                        dir_checksum, len(file_checksums)
+                    )
+                )
+                remote.index.update([dir_checksum], file_checksums)
+            yield dir_checksum
+            yield from file_checksums
 
     @staticmethod
     def _fill_statuses(checksum_info_dir, local_exists, remote_exists):
@@ -295,6 +413,7 @@ class RemoteLOCAL(RemoteBASE):
         cache = []
         path_infos = []
         names = []
+        checksums = []
         for md5, info in Tqdm(
             status_info.items(), desc="Analysing status", unit="file"
         ):
@@ -302,6 +421,7 @@ class RemoteLOCAL(RemoteBASE):
                 cache.append(self.checksum_to_path_info(md5))
                 path_infos.append(remote.checksum_to_path_info(md5))
                 names.append(info["name"])
+                checksums.append(md5)
 
         if download:
             to_infos = cache
@@ -310,7 +430,7 @@ class RemoteLOCAL(RemoteBASE):
             to_infos = path_infos
             from_infos = cache
 
-        return from_infos, to_infos, names
+        return from_infos, to_infos, names, checksums
 
     def _process(
         self,
@@ -334,14 +454,16 @@ class RemoteLOCAL(RemoteBASE):
                 file_mode=self._file_mode,
             )
             status = STATUS_DELETED
+            desc = "Downloading"
         else:
             func = remote.upload
             status = STATUS_NEW
+            desc = "Uploading"
 
         if jobs is None:
             jobs = remote.JOBS
 
-        status_info = self.status(
+        dir_status, file_status, dir_contents = self._status(
             named_cache,
             remote,
             jobs=jobs,
@@ -349,24 +471,87 @@ class RemoteLOCAL(RemoteBASE):
             download=download,
         )
 
-        plans = self._get_plans(download, remote, status_info, status)
+        dir_plans = self._get_plans(download, remote, dir_status, status)
+        file_plans = self._get_plans(download, remote, file_status, status)
 
-        if len(plans[0]) == 0:
+        total = len(dir_plans[0]) + len(file_plans[0])
+        if total == 0:
             return 0
 
-        if jobs > 1:
+        with Tqdm(total=total, unit="file", desc=desc) as pbar:
+            func = pbar.wrap_fn(func)
             with ThreadPoolExecutor(max_workers=jobs) as executor:
-                fails = sum(executor.map(func, *plans))
-        else:
-            fails = sum(map(func, *plans))
+                if download:
+                    fails = sum(executor.map(func, *dir_plans))
+                    fails += sum(executor.map(func, *file_plans))
+                else:
+                    # for uploads, push files first, and any .dir files last
+
+                    file_futures = {}
+                    for from_info, to_info, name, checksum in zip(*file_plans):
+                        file_futures[checksum] = executor.submit(
+                            func, from_info, to_info, name
+                        )
+                    dir_futures = {}
+                    for from_info, to_info, name, dir_checksum in zip(
+                        *dir_plans
+                    ):
+                        wait_futures = {
+                            future
+                            for file_checksum, future in file_futures.items()
+                            if file_checksum in dir_contents[dir_checksum]
+                        }
+                        dir_futures[dir_checksum] = executor.submit(
+                            self._dir_upload,
+                            func,
+                            wait_futures,
+                            from_info,
+                            to_info,
+                            name,
+                        )
+                    fails = sum(
+                        future.result()
+                        for future in concat(
+                            file_futures.values(), dir_futures.values()
+                        )
+                    )
 
         if fails:
             if download:
+                remote.index.clear()
                 raise DownloadError(fails)
             raise UploadError(fails)
 
-        return len(plans[0])
+        if not download:
+            # index successfully pushed dirs
+            for dir_checksum, future in dir_futures.items():
+                if future.result() == 0:
+                    file_checksums = dir_contents[dir_checksum]
+                    logger.debug(
+                        "Indexing pushed dir '{}' with "
+                        "'{}' nested files".format(
+                            dir_checksum, len(file_checksums)
+                        )
+                    )
+                    remote.index.update([dir_checksum], file_checksums)
 
+        return len(dir_plans[0]) + len(file_plans[0])
+
+    @staticmethod
+    def _dir_upload(func, futures, from_info, to_info, name):
+        for future in as_completed(futures):
+            if future.result():
+                # do not upload this .dir file if any file in this
+                # directory failed to upload
+                logger.debug(
+                    "failed to upload full contents of '{}', "
+                    "aborting .dir file upload".format(name)
+                )
+                logger.error(f"failed to upload '{from_info}' to '{to_info}'")
+                return 1
+        return func(from_info, to_info, name)
+
+    @index_locked
     def push(self, named_cache, remote, jobs=None, show_checksums=False):
         return self._process(
             named_cache,
@@ -376,6 +561,7 @@ class RemoteLOCAL(RemoteBASE):
             download=False,
         )
 
+    @index_locked
     def pull(self, named_cache, remote, jobs=None, show_checksums=False):
         return self._process(
             named_cache,
@@ -403,11 +589,10 @@ class RemoteLOCAL(RemoteBASE):
             )
             logger.warning(msg)
 
-    @staticmethod
-    def _unprotect_file(path):
+    def _unprotect_file(self, path):
         if System.is_symlink(path) or System.is_hardlink(path):
-            logger.debug("Unprotecting '{}'".format(path))
-            tmp = os.path.join(os.path.dirname(path), "." + str(uuid()))
+            logger.debug(f"Unprotecting '{path}'")
+            tmp = os.path.join(os.path.dirname(path), "." + uuid())
 
             # The operations order is important here - if some application
             # would access the file during the process of copyfile then it
@@ -424,45 +609,52 @@ class RemoteLOCAL(RemoteBASE):
                 "a symlink or a hardlink.".format(path)
             )
 
-        os.chmod(path, os.stat(path).st_mode | stat.S_IWRITE)
+        os.chmod(path, self._file_mode)
 
     def _unprotect_dir(self, path):
-        for fname in walk_files(path, self.repo.dvcignore):
-            RemoteLOCAL._unprotect_file(fname)
+        assert is_working_tree(self.repo.tree)
+
+        for fname in self.repo.tree.walk_files(path):
+            self._unprotect_file(fname)
 
     def unprotect(self, path_info):
         path = path_info.fspath
         if not os.path.exists(path):
-            raise DvcException(
-                "can't unprotect non-existing data '{}'".format(path)
-            )
+            raise DvcException(f"can't unprotect non-existing data '{path}'")
 
         if os.path.isdir(path):
             self._unprotect_dir(path)
         else:
-            RemoteLOCAL._unprotect_file(path)
+            self._unprotect_file(path)
 
-    @staticmethod
-    def protect(path_info):
-        path = fspath_py35(path_info)
-        mode = stat.S_IREAD | stat.S_IRGRP | stat.S_IROTH
+    def protect(self, path_info):
+        path = os.fspath(path_info)
+        mode = self.CACHE_MODE
 
         try:
             os.chmod(path, mode)
         except OSError as exc:
-            # In share cache scenario, we might not own the cache file, so we
+            # There is nothing we need to do in case of a read-only file system
+            if exc.errno == errno.EROFS:
+                return
+
+            # In shared cache scenario, we might not own the cache file, so we
             # need to check if cache file is already protected.
             if exc.errno not in [errno.EPERM, errno.EACCES]:
                 raise
 
-            actual = os.stat(path).st_mode
-            if actual & mode != mode:
+            actual = stat.S_IMODE(os.stat(path).st_mode)
+            if actual != mode:
                 raise
 
     def _get_unpacked_dir_path_info(self, checksum):
         info = self.checksum_to_path_info(checksum)
         return info.with_name(info.name + self.UNPACKED_DIR_SUFFIX)
 
+    def _remove_unpacked_dir(self, checksum):
+        path_info = self._get_unpacked_dir_path_info(checksum)
+        self.remove(path_info)
+
     def _path_info_changed(self, path_info):
         if self.exists(path_info) and self.state.get(path_info):
             return False
@@ -480,7 +672,7 @@ class RemoteLOCAL(RemoteBASE):
             dir_info = self.get_dir_cache(checksum)
             self._create_unpacked_dir(checksum, dir_info, unpacked_dir_info)
         except DvcException:
-            logger.warning("Could not create '{}'".format(unpacked_dir_info))
+            logger.warning(f"Could not create '{unpacked_dir_info}'")
 
             self.remove(unpacked_dir_info)
 
@@ -514,3 +706,11 @@ class RemoteLOCAL(RemoteBASE):
             if self.is_dir_checksum(c):
                 unpacked.add(c + self.UNPACKED_DIR_SUFFIX)
         return unpacked
+
+    def is_protected(self, path_info):
+        if not self.exists(path_info):
+            return False
+
+        mode = os.stat(path_info).st_mode
+
+        return stat.S_IMODE(mode) == self.CACHE_MODE

dvc/remote/oss.py

@@ -1,23 +1,19 @@
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 import logging
 import os
+import posixpath
 import threading
 
 from funcy import cached_property, wrap_prop
 
-from dvc.config import Config
 from dvc.path_info import CloudURLInfo
 from dvc.progress import Tqdm
-from dvc.remote.base import RemoteBASE
+from dvc.remote.base import BaseRemote
 from dvc.scheme import Schemes
 
-
 logger = logging.getLogger(__name__)
 
 
-class RemoteOSS(RemoteBASE):
+class OSSRemote(BaseRemote):
     """
     oss2 document:
     https://www.alibabacloud.com/help/doc-detail/32026.htm
@@ -41,25 +37,24 @@ class RemoteOSS(RemoteBASE):
     REQUIRES = {"oss2": "oss2"}
     PARAM_CHECKSUM = "etag"
     COPY_POLL_SECONDS = 5
+    LIST_OBJECT_PAGE_SIZE = 100
 
     def __init__(self, repo, config):
-        super(RemoteOSS, self).__init__(repo, config)
+        super().__init__(repo, config)
 
-        url = config.get(Config.SECTION_REMOTE_URL)
+        url = config.get("url")
         self.path_info = self.path_cls(url) if url else None
 
-        self.endpoint = config.get(Config.SECTION_OSS_ENDPOINT) or os.getenv(
-            "OSS_ENDPOINT"
-        )
+        self.endpoint = config.get("oss_endpoint") or os.getenv("OSS_ENDPOINT")
 
         self.key_id = (
-            config.get(Config.SECTION_OSS_ACCESS_KEY_ID)
+            config.get("oss_key_id")
             or os.getenv("OSS_ACCESS_KEY_ID")
             or "defaultId"
         )
 
         self.key_secret = (
-            config.get(Config.SECTION_OSS_ACCESS_KEY_SECRET)
+            config.get("oss_key_secret")
             or os.getenv("OSS_ACCESS_KEY_SECRET")
             or "defaultSecret"
         )
@@ -69,9 +64,9 @@ class RemoteOSS(RemoteBASE):
     def oss_service(self):
         import oss2
 
-        logger.debug("URL: {}".format(self.path_info))
-        logger.debug("key id: {}".format(self.key_id))
-        logger.debug("key secret: {}".format(self.key_secret))
+        logger.debug(f"URL: {self.path_info}")
+        logger.debug(f"key id: {self.key_id}")
+        logger.debug(f"key secret: {self.key_secret}")
 
         auth = oss2.Auth(self.key_id, self.key_secret)
         bucket = oss2.Bucket(auth, self.endpoint, self.path_info.bucket)
@@ -92,17 +87,25 @@ class RemoteOSS(RemoteBASE):
         if path_info.scheme != self.scheme:
             raise NotImplementedError
 
-        logger.debug("Removing oss://{}".format(path_info))
+        logger.debug(f"Removing oss://{path_info}")
         self.oss_service.delete_object(path_info.path)
 
-    def _list_paths(self, prefix):
+    def _list_paths(self, prefix, progress_callback=None):
         import oss2
 
         for blob in oss2.ObjectIterator(self.oss_service, prefix=prefix):
+            if progress_callback:
+                progress_callback()
             yield blob.key
 
-    def list_cache_paths(self):
-        return self._list_paths(self.path_info.path)
+    def list_cache_paths(self, prefix=None, progress_callback=None):
+        if prefix:
+            prefix = posixpath.join(
+                self.path_info.path, prefix[:2], prefix[2:]
+            )
+        else:
+            prefix = self.path_info.path
+        return self._list_paths(prefix, progress_callback)
 
     def _upload(
         self, from_file, to_info, name=None, no_progress_bar=False, **_kwargs