Add workflow for testing with all deps (#4410)

# Add action to test with all dependencies installed

PR adds a custom action for setting up poetry that allows specifying a
cache key:
https://github.com/actions/setup-python/issues/505#issuecomment-1273013236

This makes it possible to run 2 types of unit tests: 

(1) unit tests with only core dependencies
(2) unit tests with extended dependencies (e.g., those that rely on an
optional pdf parsing library)


As part of this PR, we're moving some pdf parsing tests into the
unit-tests section and making sure that these unit tests get executed
when running with extended dependencies.

.github/actions/poetry_setup/action.yml

@@ -0,0 +1,64 @@
+# An action for setting up poetry install with caching.
+# Using a custom action since the default action does not
+# take poetry install groups into account.
+# Action code from:
+# https://github.com/actions/setup-python/issues/505#issuecomment-1273013236
+name: poetry-install-with-caching
+description: Poetry install with support for caching of dependency groups.
+
+inputs:
+  python-version:
+    description: Python version, supporting MAJOR.MINOR only
+    required: true
+
+  poetry-version:
+    description: Poetry version
+    required: true
+
+  install-command:
+    description: Command run for installing dependencies
+    required: false
+    default: poetry install
+
+  cache-key:
+    description: Cache key to use for manual handling of caching
+    required: true
+
+  working-directory:
+    description: Directory to run install-command in
+    required: false
+    default: ""
+
+runs:
+  using: composite
+  steps:
+    - uses: actions/setup-python@v4
+      with:
+        python-version: ${{ inputs.python-version }}
+
+    - uses: actions/cache@v3
+      id: cache-pip
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "15"
+      with:
+        path: |
+          ~/.cache/pip
+        key: pip-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}
+
+    - run: pipx install poetry==${{ inputs.poetry-version }} --python python${{ inputs.python-version }}
+      shell: bash
+
+    - uses: actions/cache@v3
+      id: cache-poetry
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "15"
+      with:
+        path: |
+          ~/.cache/pypoetry/virtualenvs
+          ~/.cache/pypoetry/cache
+          ~/.cache/pypoetry/artifacts
+        key: poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-poetry-${{ inputs.poetry-version }}-${{ inputs.cache-key }}-${{ hashFiles('poetry.lock') }}
+
+    - run: ${{ inputs.install-command }}
+      working-directory: ${{ inputs.working-directory }}
+      shell: bash

.github/workflows/test.yml

@@ -20,15 +20,13 @@ jobs:
           - "3.11"
     steps:
       - uses: actions/checkout@v3
-      - name: Install poetry
-        run: pipx install poetry==$POETRY_VERSION
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-      - name: Install dependencies
-        run: poetry install
+          poetry-version: "1.4.2"
+          cache-key: "main"
+          install-command: "poetry install"
       - name: Run unit tests
         run: |
           make test

.github/workflows/test_all.yml

@@ -0,0 +1,33 @@
+# Run unit tests with all optional packages installed.
+name: test_all
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+
+env:
+  POETRY_VERSION: "1.4.2"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: "1.4.2"
+          cache-key: "extended"
+          install-command: "poetry install -E extended_testing"
+      - name: Run unit tests
+        run: |
+          make test