Merge branch 'data-validation-py312-1.17-e1' into data-validation-py312-1.17-e

Author: pritamdodeja

.bazelrc

@@ -1,11 +1,14 @@
 # Needed to work with ZetaSQL dependency.
+# Zetasql is removed.
+# This is a candidate for removal
 build --cxxopt="-std=c++17"
 
 # Needed to avoid zetasql proto error.
+# Zetasql is removed.
+# This is a candidate for removal
 build --protocopt=--experimental_allow_proto3_optional
 
 # icu@: In create_linking_context: in call to create_linking_context(),
 # parameter 'user_link_flags' is deprecated and will be removed soon.
 # It may be temporarily re-enabled by setting --incompatible_require_linker_input_cc_api=false
 build --incompatible_require_linker_input_cc_api=false
-

.bazelversion

@@ -1 +1 @@
-6.5.0
+6.5.0

.github/reusable-build/action.yml

@@ -0,0 +1,36 @@
+name: Resusable steps to build data-validation
+
+inputs:
+  python-version:
+    description: 'Python version'
+    required: true
+  upload-artifact:
+    description: 'Should upload build artifact or not'
+    default: false
+
+runs:
+  using: 'composite'
+  steps:
+  - name: Set up Python ${{ inputs.python-version }}
+    uses: actions/setup-python@v5
+    with:
+      python-version: ${{ inputs.python-version }}
+
+  - name: Build the package for Python ${{ inputs.python-version }}
+    shell: bash
+    run: |
+      version="${{ matrix.python-version }}"
+      docker compose run -e PYTHON_VERSION=$(echo "$version" | sed 's/\.//') manylinux2010
+
+  - name: Upload wheel artifact for Python ${{ matrix.python-version }}
+    if: ${{ inputs.upload-artifact == 'true' }}
+    uses: actions/upload-artifact@v4
+    with:
+      name: data-validation-wheel-py${{ matrix.python-version }}
+      path: dist/*.whl
+
+  - name: Check the wheel
+    shell: bash
+    run: |
+      pip install twine
+      twine check dist/*

.github/workflows/build.yml

@@ -0,0 +1,54 @@
+name: Build
+
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches:
+      - master
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11"]
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+
+    - name: Build data-validation
+      id: build-data-validation
+      uses: ./.github/reusable-build
+      with:
+        python-version: ${{ matrix.python-version }}
+        upload-artifact: true
+
+  upload_to_pypi:
+    name: Upload to PyPI
+    runs-on: ubuntu-latest
+    if: (github.event_name == 'release' && startsWith(github.ref, 'refs/tags')) || (github.event_name == 'workflow_dispatch')
+    needs: [build]
+    environment:
+      name: pypi
+      url: https://pypi.org/p/tensorflow-data-validation/
+    permissions:
+      id-token: write
+    steps:
+      - name: Retrieve wheels
+        uses: actions/download-artifact@v4.1.8
+        with:
+          merge-multiple: true
+          path: wheels
+
+      - name: List the build artifacts
+        run: |
+          ls -lAs wheels/
+
+      - name: Upload to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1.9
+        with:
+          packages_dir: wheels/

.github/workflows/ci-lint.yml

@@ -0,0 +1,21 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+     branches: [master]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4.1.7
+      with:
+        # Ensure the full history is fetched
+        # This is required to run pre-commit on a specific set of commits
+        # TODO: Remove this when all the pre-commit issues are fixed
+        fetch-depth: 0
+    - uses: actions/setup-python@v5.1.1
+      with:
+        python-version: 3.13
+    - uses: pre-commit/action@v3.0.1

.github/workflows/docs.yml

@@ -0,0 +1,52 @@
+name: Deploy docs
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - 'master'
+  pull_request:
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email 41898282+github-actions[bot]@users.noreply.github.com
+        if: (github.event_name != 'pull_request')
+
+      - name: Set up Python 3.9
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.9'
+          cache: 'pip'
+          cache-dependency-path: |
+            setup.py
+            requirements-docs.txt
+
+      - name: Save time for cache for mkdocs
+        run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
+
+      - name: Caching
+        uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
+
+      - name: Install Dependencies
+        run: pip install -r requirements-docs.txt
+
+      - name: Deploy to GitHub Pages
+        run: mkdocs gh-deploy --force
+        if: (github.event_name != 'pull_request')
+
+      - name: Build docs to check for errors
+        run: mkdocs build
+        if: (github.event_name == 'pull_request')

.github/workflows/test.yml

@@ -0,0 +1,40 @@
+name: Test
+
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches:
+      - master
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11"]
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+
+    - name: Build data-validation
+      id: build-data-validation
+      uses: ./.github/reusable-build
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install built wheel
+      shell: bash
+      run: |
+        PYTHON_VERSION_TAG="cp$(echo ${{ matrix.python-version }} | sed 's/\.//')"
+        WHEEL_FILE=$(ls dist/*${PYTHON_VERSION_TAG}*.whl)
+        pip install "${WHEEL_FILE}[test]"
+
+    - name: Run Test
+      run: |
+        rm -rf bazel-*
+        # run tests
+        pytest -vv

.gitignore

@@ -126,4 +126,4 @@ dmypy.json
 .pyre/
 
 # pb2.py files
-*_pb2.py
+*_pb2.py

.pre-commit-config.yaml

@@ -0,0 +1,39 @@
+# pre-commit is a tool to perform a predefined set of tasks manually and/or
+# automatically before git commits are made.
+#
+# Config reference: https://pre-commit.com/#pre-commit-configyaml---top-level
+#
+# Common tasks
+#
+# - Register git hooks: pre-commit install --install-hooks
+# - Run on all files:   pre-commit run --all-files
+#
+# These pre-commit hooks are run as CI.
+#
+# NOTE: if it can be avoided, add configs/args in pyproject.toml or below instead of creating a new `.config.file`.
+# https://pre-commit.ci/#configuration
+ci:
+  autoupdate_schedule: monthly
+  autofix_commit_msg: |
+    [pre-commit.ci] Apply automatic pre-commit fixes
+
+repos:
+  # general
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: end-of-file-fixer
+        exclude: '\.svg$|\.patch$'
+      - id: trailing-whitespace
+        exclude: '\.svg$|\.patch$'
+      - id: check-json
+      - id: check-yaml
+        args: [--allow-multiple-documents, --unsafe]
+      - id: check-toml
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.6
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format

README.md

@@ -238,4 +238,3 @@ tag.
   * [TensorFlow Data Validation PyPI](https://pypi.org/project/tensorflow-data-validation/)
   * [TensorFlow Data Validation Paper](https://mlsys.org/Conferences/2019/doc/2019/167.pdf)
   * [TensorFlow Data Validation Slides](https://conf.slac.stanford.edu/xldb2018/sites/xldb2018.conf.slac.stanford.edu/files/Tues_09.45_NeoklisPolyzotis_Data%20Analysis%20and%20Validation%20(1).pdf)
-