Add python, markdown and github action linter (#5)

to ensure the code maintenance. Thanks to docling
project- took some good bits around python linting
from the project.

These checks are also added in the markdown, so that
user can run these checks locally to recreate the
errors.

Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com>

.github/actions/setup-poetry/action.yml

@@ -0,0 +1,19 @@
+name: 'Set up Poetry and install'
+description: 'Set up a specific version of Poetry and install dependencies using caching.'
+inputs:
+  python-version:
+    description: "Version range or exact version of Python or PyPy to use, using SemVer's version range syntax."
+    default: '3.11'
+runs:
+  using: 'composite'
+  steps:
+    - name: Install poetry
+      run: pipx install poetry==1.8.3
+      shell: bash
+    - uses: actions/setup-python@v4
+      with:
+        python-version: ${{ inputs.python-version }}
+        cache: 'poetry'
+    - name: Install dependencies
+      run: poetry install --all-extras
+      shell: bash

.github/workflows/actionlint.yml

@@ -0,0 +1,23 @@
+name: Lint GitHub Actions workflows
+on:
+  push:
+    branches: ["main"]
+    paths:
+      - '.github/**'
+  pull_request:
+    branches: ["main"]
+    paths:
+      - '.github/**'
+
+jobs:
+  actionlint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Download actionlint
+        id: get_actionlint
+        run: bash <(curl https://raw.githubusercontent.com/rhysd/actionlint/main/scripts/download-actionlint.bash)
+        shell: bash
+      - name: Check workflow files
+        run: PATH=".:$PATH" make action-lint
+        shell: bash

.github/workflows/checks.yml

@@ -0,0 +1,34 @@
+name: Run linter checks
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    branches: ["main"]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  py-lint:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.11']
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/setup-poetry
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Run styling check
+        run: poetry run pre-commit run --all-files
+
+  markdown-lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: markdownlint-cli2-action
+        uses: DavidAnson/markdownlint-cli2-action@v16
+        with:
+          globs: "**/*.md"
+

.gitignore

@@ -441,3 +441,4 @@ pip-selfcheck.json
 
 # Makefile
 .action-lint
+.markdown-lint

.markdownlint-cli2.yaml

@@ -0,0 +1,6 @@
+config:
+  line-length: false
+  no-emphasis-as-header: false
+  first-line-heading: false
+globs:
+  - "**/*.md"

CODE_OF_CONDUCT.md

@@ -115,7 +115,7 @@ the community.
 
 ## Attribution
 
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org)],
 version 2.0, available at
 [https://www.contributor-covenant.org/version/2/0/code_of_conduct.html](https://www.contributor-covenant.org/version/2/0/code_of_conduct.html).
 
@@ -126,4 +126,4 @@ Homepage: [https://www.contributor-covenant.org](https://www.contributor-covenan
 
 For answers to common questions about this code of conduct, see the FAQ at
 [https://www.contributor-covenant.org/faq](https://www.contributor-covenant.org/faq). Translations are available at
-[https://www.contributor-covenant.org/translations](https://www.contributor-covenant.org/translations).
+[https://www.contributor-covenant.org/translations](https://www.contributor-covenant.org/translations).

CONTRIBUTING.md

@@ -1,4 +1,5 @@
 ## Contributing In General
+
 Our project welcomes external contributions. If you have an itch, please feel
 free to scratch it.
 
@@ -34,14 +35,13 @@ maintainers of each component affected.
 
 For a list of the maintainers, see the [MAINTAINERS.md](MAINTAINERS.md) page.
 
-
 ## Legal
 
 Each source file must include a license header for the MIT
 Software. Using the SPDX format is the simplest approach.
 e.g.
 
-```
+```text
 /*
 Copyright IBM Inc. All rights reserved.
 
@@ -60,54 +60,54 @@ must include a sign-off statement in the commit message.
 Here is an example Signed-off-by line, which indicates that the
 submitter accepts the DCO:
 
-```
+```text
 Signed-off-by: John Doe <john.doe@example.com>
 ```
 
 You can include this automatically when you commit a change to your
 local git repository using the following command:
 
-```
+```text
 git commit -s
 ```
 
-
 ## Communication
 
 Please feel free to connect with us using the [discussion section](https://github.com/DS4SD/docling-serve/discussions).
 
-
-
 ## Developing
 
 ### Usage of Poetry
 
 We use Poetry to manage dependencies.
 
-
 #### Install
 
-To install, see the documentation here: https://python-poetry.org/docs/master/#installing-with-the-official-installer
+To install, see the documentation here: <https://python-poetry.org/docs/master/#installing-with-the-official-installer>
 
 1. Install the Poetry globally in your machine
+
     ```bash
     curl -sSL https://install.python-poetry.org | python3 -
     ```
+
     The installation script will print the installation bin folder `POETRY_BIN` which you need in the next steps.
 
 2. Make sure Poetry is in your `$PATH`
     - for `zsh`
+
         ```sh
         echo 'export PATH="POETRY_BIN:$PATH"' >> ~/.zshrc
         ```
+
     - for `bash`
+
         ```sh
         echo 'export PATH="POETRY_BIN:$PATH"' >> ~/.bashrc
         ```
 
 3. The official guidelines linked above include useful details on the configuration of autocomplete for most shell environments, e.g. Bash and Zsh.
 
-
 #### Create a Virtual Environment and Install Dependencies
 
 To activate the Virtual Environment, run:
@@ -122,7 +122,7 @@ To spawn a shell with the Virtual Environment activated. If the Virtual Environm
 poetry install
 ```
 
-**(Advanced) Use a Specific Python Version**
+#### (Advanced) Use a Specific Python Version
 
 If for whatever reason you need to work in a specific (older) version of Python, run:
 
@@ -132,7 +132,6 @@ poetry env use $(which python3.10)
 
 This creates a Virtual Environment with Python 3.10. For other versions, replace `$(which python3.10)` by the path to the interpreter (e.g., `/usr/bin/python3.8`) or use `$(which pythonX.Y)`.
 
-
 #### Add a new dependency
 
 ```bash
@@ -146,7 +145,6 @@ We use the following tools to enforce code style:
 - iSort, to sort imports
 - Black, to format code
 
-
 We run a series of checks on the code base on every commit, using `pre-commit`. To install the hooks, run:
 
 ```bash
@@ -155,10 +153,8 @@ pre-commit install
 
 To run the checks on-demand, run:
 
-```
+```shell
 pre-commit run --all-files
 ```
 
 Note: Checks like `Black` and `isort` will "fail" if they modify files. This is because `pre-commit` doesn't like to see files modified by their Hooks. In these cases, `git add` the modified files and `git commit` again.
-
-

Makefile

@@ -18,9 +18,12 @@ endif
 
 TAG=$(shell git rev-parse HEAD)
 
-lint:
+action-lint-file:
 	$(CMD_PREFIX) touch .action-lint
 
+md-lint-file:
+	$(CMD_PREFIX) touch .markdown-lint
+
 .PHONY: docling-serve-cpu-image
 docling-serve-cpu-image: Containerfile ## Build docling-serve "cpu only" continaer image
 	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve CPU ONLY]"
@@ -37,7 +40,7 @@ docling-serve-gpu-image: Containerfile ## Build docling-serve continaer image wi
 
 .PHONY: action-lint
 action-lint: .action-lint ##      Lint GitHub Action workflows
-.action-lint: $(shell find .github -type f) | lint
+.action-lint: $(shell find .github -type f) | action-lint-file
 	$(ECHO_PREFIX) printf "  %-12s .github/...\n" "[ACTION LINT]"
 	$(CMD_PREFIX) if ! which actionlint $(PIPE_DEV_NULL) ; then \
 		echo "Please install actionlint." ; \
@@ -51,3 +54,22 @@ action-lint: .action-lint ##      Lint GitHub Action workflows
 	fi
 	$(CMD_PREFIX) actionlint -color
 	$(CMD_PREFIX) touch $@
+
+.PHONY: md-lint
+md-lint: .md-lint ##      Lint markdown files
+.md-lint: $(wildcard */**/*.md) | md-lint-file
+	$(ECHO_PREFIX) printf "  %-12s ./...\n" "[MD LINT]"
+	$(CMD_PREFIX) docker run --rm -v $$(pwd):/workdir davidanson/markdownlint-cli2:v0.14.0 "**/*.md"
+	$(CMD_PREFIX) touch $@
+
+
+.PHONY: py-Lint
+py-lint: ##      Lint Python files
+	$(ECHO_PREFIX) printf "  %-12s ./...\n" "[PY LINT]"
+	$(CMD_PREFIX) if ! which poetry $(PIPE_DEV_NULL) ; then \
+		echo "Please install poetry." ; \
+		echo "pip install poetry" ; \
+		exit 1 ; \
+	fi
+	$(CMD_PREFIX) poetry install --all-extras
+	$(CMD_PREFIX) poetry run pre-commit run --all-files

README.md

@@ -5,7 +5,6 @@
  > [!NOTE]
 > This is an unstable draft implementation which will quickly evolve.
 
-
 ## Development
 
 Install the dependencies