Refresh

.github/dependabot.yml

@@ -0,0 +1,19 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://help.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+
+version: 2
+updates:
+  - package-ecosystem: "pip" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    ignore:
+      # Optional: Official actions have moving tags like v1;
+      # if you use those, you don't need updates.
+      - dependency-name: "actions/*"

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,70 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ master ]
+  schedule:
+    - cron: '17 21 * * 4'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Learn more about CodeQL language support at https://git.io/codeql-language-support
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v3
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v2
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v2
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+
+    #- run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v2

.github/workflows/lock.yml

@@ -0,0 +1,22 @@
+name: 'Lock Threads'
+
+on:
+  schedule:
+    - cron: '0 0 1/7 * *'
+  workflow_dispatch:
+
+permissions:
+  issues: write
+
+concurrency:
+  group: lock
+
+jobs:
+  action:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: dessant/lock-threads@v3
+        with:
+          process-only: 'issues'
+          issue-inactive-days: '14'
+          log-output: true

.github/workflows/pythonpackage.yml

@@ -0,0 +1,112 @@
+name: tests
+
+on: [push, pull_request]
+
+jobs:
+  format:
+    # We want all subsequent steps of CI to refer to the fresh version of code,
+    # so run this before anything else.
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v1
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.10"
+      - name: Install Black
+        run: pip install black
+      - name: Run black --check .
+        run: black --check .
+      - name: If needed, commit black changes to the pull request
+        if: failure()
+        run: |
+          black .
+          git config --global user.name 'autoblack'
+          git config --global user.email 'cclauss@users.noreply.github.com'
+          git remote set-url origin https://x-access-token:${{ secrets.GITHUB_TOKEN }}@github.com/$GITHUB_REPOSITORY
+          git checkout $GITHUB_HEAD_REF
+          git commit -am "fixup: Format Python code with Black"
+          git push
+  test:
+    needs: format
+    timeout-minutes: 30
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [windows-latest, macos-latest, ubuntu-latest]
+        python-version: [3.7, 3.8, 3.9, "3.10"]
+
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        pip install --upgrade pip
+        pip install -e .
+    - name: Install test dependencies
+      run: |        
+        pip install -r requirements.txt
+    - name: pytest
+      run: |
+         pytest tests dedupe --cov dedupe
+    - env:
+        COVERALLS_PARALLEL: true
+        COVERALLS_REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        COVERALLS_FLAG_NAME: job-${{ matrix.os}}-${{ matrix.python-version }}
+      name: Submit to coveralls
+      run: |
+        pip install https://github.com/bboe/coveralls-python/archive/github_actions.zip
+        coveralls
+    - name: flake8
+      run: |
+         flake8 dedupe tests
+    - name: Static Testing
+      run: |        
+        mypy --ignore-missing-imports dedupe
+    - name: Integration test, record link
+      run: |
+        python tests/canonical_gazetteer.py -vv
+        python tests/canonical_matching.py -vv
+    - name: Integration test, dedupe
+      run: |
+        python tests/canonical.py -vv
+  finish:
+    needs: test
+    runs-on: ubuntu-latest
+    steps:
+    - name: Coveralls Finished
+      uses: coverallsapp/github-action@57daa114ba54fd8e1c8563e8027325c0bf2f5e80
+      with:
+        github-token: ${{ secrets.GITHUB_TOKEN }}
+        parallel-finished: true
+  wheels:
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags')
+    needs: test
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [windows-latest, macos-latest, ubuntu-latest]
+    steps:
+    - uses: actions/checkout@v1
+    - uses: actions/setup-python@v2    
+    - name: Build wheels
+      uses: pypa/cibuildwheel@2.5.0
+      env:
+        CIBW_ARCHS_MACOS: x86_64 arm64 universal2
+    - name: Build sdist
+      run: |
+        pip install build
+        python -m build --sdist
+    - name: Publish wheels to PyPI
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+      run: |
+        pip install twine
+        twine upload --skip-existing wheelhouse/*.whl
+        twine upload dist/*
+      continue-on-error: true

.gitignore

@@ -1,3 +1,7 @@
+.env
+.coverage*
+cpredicates.c
+*.code-workspace
 libdistance-0.2.1
 build
 _build
@@ -27,4 +31,4 @@ dedupe.egg-info/
 ENV
 dist
 .coverage
-src/*.c
+src/*.c

.readthedocs.yml

@@ -0,0 +1,23 @@
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Build documentation with MkDocs
+#mkdocs:
+#  configuration: mkdocs.yml
+
+# Optionally build your docs in additional formats such as PDF and ePub
+formats: all
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  version: 3.7
+  install:
+    - requirements: docs/requirements.txt
+    - method: pip
+      path: .