Merge pull request #47 from GateNLP/develop

Release 1.0.0 rc1

.github/workflows/lint.yml

@@ -0,0 +1,38 @@
+name: Lint
+
+on:
+  push:
+    branches:
+      - master
+      - develop
+  pull_request:
+    branches:
+      - master
+      - develop
+
+permissions:
+  contents: read
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Poetry
+        run: pipx install poetry==1.8.3
+      - name: Setup Python 3.8
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.8"
+          cache: "poetry"
+      - name: Install dependencies
+        run: poetry install --no-interaction --no-root
+      - name: Install Project
+        run: poetry install --no-interaction
+      - name: Ruff Lint Format
+        run: poetry run ruff format --check
+        id: format
+      - name: Ruff Lint Check
+        run: poetry run ruff check --output-format=github
+        if: success() || steps.format.conclusion == 'failure'

.github/workflows/publish.yml

@@ -0,0 +1,111 @@
+name: Push to PyPI
+
+on:
+  push:
+    tags:
+      - '*'
+  workflow_dispatch:
+
+jobs:
+  build:
+    name: Build Distribution
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Poetry
+        run: pipx install poetry==1.8.3
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.8"
+          cache: "poetry"
+      - name: Install Python dependencies
+        run: poetry install --no-interaction --no-root
+      - name: Build
+        run: poetry build
+      - name: Store distribution packages
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+  publish-to-pypi:
+    name: Publish to PyPI
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/ultimate-sitemap-parser
+    permissions:
+      id-token: write
+    steps:
+      - name: Download distribution packages
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  github-release:
+    name: GitHub release
+    needs:
+      - publish-to-pypi
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write
+      id-token: write
+
+    steps:
+    - name: Download distribution packages
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Sign the dists with Sigstore
+      uses: sigstore/[email protected]
+      with:
+        inputs: >-
+          ./dist/*.tar.gz
+          ./dist/*.whl
+    - name: Create GitHub Release
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+      run: >-
+        gh release create
+        '${{ github.ref_name }}'
+        --repo '${{ github.repository }}'
+        --notes ""
+    - name: Upload artifact signatures to GitHub Release
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+      # Upload to GitHub Release using the `gh` CLI.
+      # `dist/` contains the built packages, and the
+      # sigstore-produced signatures and certificates.
+      run: >-
+        gh release upload
+        '${{ github.ref_name }}' dist/**
+        --repo '${{ github.repository }}'
+
+  publish-to-testpypi:
+    name: Publish to TestPyPI
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/ultimate-sitemap-parser
+    permissions:
+      id-token: write
+    steps:
+      - name: Download distribution packages
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Publish to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/

.github/workflows/test.yml

@@ -0,0 +1,41 @@
+name: Test
+
+on:
+  push:
+    branches:
+      - master
+      - develop
+  pull_request:
+    branches:
+      - master
+      - develop
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Poetry
+        run: pipx install poetry==1.8.3
+      - name: Setup Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+      - name: Install dependencies
+        run: poetry install --no-interaction --no-root
+      - name: Install Project
+        run: poetry install --no-interaction
+      - name: Poetry Build
+        run: poetry build
+      - name: Run tests
+        run: poetry run pytest

.github/workflows/test_integration.yml

@@ -0,0 +1,43 @@
+name: Integration Test
+
+on: [workflow_dispatch]
+
+permissions:
+  contents: read
+
+jobs:
+  integ_test:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        python-version: ["3.8"]
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Poetry
+        run: pipx install poetry==1.8.3
+      - name: Setup Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+      - name: Install dependencies
+        run: poetry install --no-interaction --no-root
+      - name: Install Project
+        run: poetry install --no-interaction
+      - name: Cache cassettes
+        uses: actions/cache@v4
+        with:
+          path: tests/integration/cassettes
+          # Always restore this cache as the script takes care of updating
+          key: usp-cassettes
+      - name: Download cassettes
+        run: poetry run python tests/integration/download.py -d
+      - name: Run integration tests
+        run: poetry run pytest --integration --durations=0 --junit-xml=integration.xml tests/integration/test_integration.py
+      - name: Upload report
+        uses: actions/upload-artifact@v4
+        with:
+          path: $GITHUB_SHA.xml
+          name: junit_report

.gitignore

@@ -114,70 +114,7 @@ dmypy.json
 # Pyre type checker
 .pyre/
 
-# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
-# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
-
-# User-specific stuff
-.idea/**/workspace.xml
-.idea/**/tasks.xml
-.idea/**/usage.statistics.xml
-.idea/**/dictionaries
-.idea/**/shelf
-
-# Generated files
-.idea/**/contentModel.xml
-
-# Sensitive or high-churn files
-.idea/**/dataSources/
-.idea/**/dataSources.ids
-.idea/**/dataSources.local.xml
-.idea/**/sqlDataSources.xml
-.idea/**/dynamic.xml
-.idea/**/uiDesigner.xml
-.idea/**/dbnavigator.xml
-
-# Gradle
-.idea/**/gradle.xml
-.idea/**/libraries
-
-# Gradle and Maven with auto-import
-# When using Gradle or Maven with auto-import, you should exclude module files,
-# since they will be recreated, and may cause churn.  Uncomment if using
-# auto-import.
-# .idea/modules.xml
-# .idea/*.iml
-# .idea/modules
-
-# CMake
-cmake-build-*/
-
-# Mongo Explorer plugin
-.idea/**/mongoSettings.xml
-
-# File-based project format
-*.iws
-
-# IntelliJ
-out/
-
-# mpeltonen/sbt-idea plugin
-.idea_modules/
-
-# JIRA plugin
-atlassian-ide-plugin.xml
-
-# Cursive Clojure plugin
-.idea/replstate.xml
-
-# Crashlytics plugin (for Android Studio and IntelliJ)
-com_crashlytics_export_strings.xml
-crashlytics.properties
-crashlytics-build.properties
-fabric.properties
-
-# Editor-based Rest Client
-.idea/httpRequests
-
-# Android studio 3.1+ serialized cache file
-.idea/caches/build_file_checksums.ser
+.idea/
 
+# Memray reports
+memray/