build: add CI/CD

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @elijas

.github/SECURITY.md

@@ -0,0 +1,17 @@
+## Security
+
+Alphanome.AI takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations.
+
+If you believe you have found a security vulnerability in any Alphanome.AI-owned repository, please report it to us as described below.
+
+## Reporting Security Issues
+
+**Please do not report security vulnerabilities through public GitHub issues.**
+
+Instead, please report them to **[email protected]** (alternatively, [email protected]).
+
+You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message.
+
+## Preferred Languages
+
+We prefer all communications to be in English.

.github/workflows/check.yml

@@ -0,0 +1,46 @@
+name: CI/CD Checks
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ['3.7', '3.8', '3.9', '3.10']
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install Poetry
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+
+    - name: Cache Poetry dependencies
+      uses: actions/cache@v2
+      with:
+        path: ~/.cache/pypoetry
+        key: ${{ runner.os }}-poetry-${{ matrix.python-version }}-${{ hashFiles('**/pyproject.toml') }}
+        restore-keys: |
+          ${{ runner.os }}-poetry-${{ matrix.python-version }}-
+          ${{ runner.os }}-poetry-
+          ${{ runner.os }}-
+
+    - name: Install dependencies
+      run: poetry install
+
+    - name: Run Taskfile "ci-cd-checks"
+      run: task ci-cd-checks

.github/workflows/release.yml

@@ -0,0 +1,44 @@
+name: Release to PyPI
+
+on:
+  push:
+    tags:
+      - '[0-9]+.[0-9]+.[0-9]+'
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.11'
+
+    - name: Install Poetry
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+
+    - name: Cache Poetry dependencies
+      uses: actions/cache@v2
+      with:
+        path: ~/.cache/pypoetry
+        key: ${{ runner.os }}-poetry-3.11-${{ hashFiles('**/pyproject.toml') }}
+        restore-keys: |
+          ${{ runner.os }}-poetry-3.11-
+          ${{ runner.os }}-poetry-
+          ${{ runner.os }}-
+
+    - name: Install dependencies
+      run: poetry install
+
+    - name: Build package
+      run: poetry build
+
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        user: __token__
+        password: ${{ secrets.PUBLIC_PYPI_API_TOKEN }}

.pre-commit-config.yaml

@@ -6,9 +6,9 @@ repos:
 
   - repo: local
     hooks:
-      - id: task-prepare
-        name: Run task prepare
-        entry: task prepare
+      - id: pre-commit-tasks
+        name: Run pre-commit tasks
+        entry: task pre-commit
         language: system
         pass_filenames: false
         stages: [commit]

Taskfile.yml

@@ -1,51 +1,86 @@
 version: '3'
 
 tasks:
+
+#####################################
+### Composite Tasks and Shortcuts ###
+#####################################
+
+  pre-commit: 
+    desc: Composite task to run all quick checks.
+    cmds:
+      - task unit
+      - task lint-fix
+      - task e2e-smoke
+
+  p:
+    desc: Shortcut for `task pre-commit`.
+    deps:
+      - pre-commit
+
+  ci-cd-checks:
+    desc: Composite task to run all CI/CD checks.
+    cmds:
+      - task unit
+      - task lint
+      - task e2e
+
+######################
+### Run Unit Tests ###
+######################
+
   unit:
     desc: Run unit tests and check code coverage.
     cmds:
       # Recommended coverage viewer in VSCode: https://marketplace.visualstudio.com/items?itemName=ryanluker.vscode-coverage-gutters
       - pytest -s --cov --cov-report=lcov:lcov.info --cov-report=term:skip-covered --cov-fail-under=60 tests/unit/
 
   unit-watch:
-    desc: Run unit tests and check code coverage when files change.
+    desc: Run unit tests and check code coverage immediately when files change.
     cmds:
       # Recommended coverage viewer in VSCode: https://marketplace.visualstudio.com/items?itemName=ryanluker.vscode-coverage-gutters
-      - ptw
+      - ptw -- -s --cov --cov-report=lcov:lcov.info --cov-report=term:skip-covered --cov-fail-under=60 tests/unit/
+
+
+###############################
+### Code Quality Checks ###
+###############################
 
   lint:
-    desc: Lint the code.
+    desc: Lint the code without auto-fixing issues.
+    cmds:
+      - ruff check sec_parser/
+      - mypy
+
+  lint-fix:
+    desc: Lint the code and auto-fix issues.
     cmds:
       - ruff check --fix sec_parser/
       - mypy
 
+############################
+### Run End-to-end Tests ###
+############################
+
   e2e:
     desc: Run repeated end-to-end tests.
     cmds:
-      - python -m tests.e2e.sec_parser
+      # The CLI_ARGS variable allows passing custom arguments to the end-to-end test after "--". 
+      # For instance, to run the test with specific parameters, use the command: 
+      # task e2e -- --tests-per-core=5 --cores=2 --limit_documents=2
+      - python -m tests.e2e.sec_parser {{.CLI_ARGS}}
 
   e2e-smoke:
-    desc: Run a single end-to-end test per document. This is a useful way to verify if the parser is functioning (a so-called "smoke" test).
+    desc: Run a single end-to-end test for a single document. This is a useful way to verify if the parser is functioning (a so-called "smoke" test).
     cmds:
-      - python -m tests.e2e.sec_parser --tests-per-core=1 --cores=1
+      - python -m tests.e2e.sec_parser --tests-per-core=1 --cores=1 --limit_documents=1
 
-  e2e-watch:
-    desc: Run repeated end-to-end tests every 10 minutes.
-    cmds:
-      - watch -n 600 task e2e
-
-  prepare: 
-    desc: Lint the code and run all quick checks.
-    cmds:
-      - task unit && task lint && task e2e-smoke # Executing in this order instead of using Taskfile's `deps` to control the order of execution
-
-  p:
-    desc: Shortcut for `task prepare`.
-    deps:
-      - prepare
+#######################
+### Developer Tools ###
+#######################
 
   visual:
-    desc: Run the parser output visualizer (used for debugging and demos).
+    desc: Run the parser output visualizer (used for debugging and demos). This will open a browser window with the user interface.
     cmds:
       # PYTHONPATH is added to make streamlit watch file changes. Read more: https://docs.streamlit.io/knowledge-base/using-streamlit/streamlit-watch-changes-other-modules-importing-app
       - PYTHONPATH=$PYTHONPATH:$(pwd)/sec_parser streamlit run debug_tools/parser_output_visualizer/app.py --server.runOnSave=true