make package and use formatters etc

make use of pre-commit to run code formatting tools

Add code format checks to ci

reorganize code to a python package

.github/workflows/unit-tests.yml → .github/workflows/tests.yml

@@ -1,16 +1,23 @@
-name: Unit Tests
+name: Tests
 
-on: [push, pull_request]
+on: push
 
 jobs:
-  test:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - uses: actions/setup-python@v3
+    - uses: pre-commit/[email protected]
+  tox-tests:
     runs-on: ubuntu-latest
 
     strategy:
       matrix:
         python-version: [3.9]
 
     steps:
+
       - name: Checkout repository
         uses: actions/checkout@v2
 
@@ -30,12 +37,16 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install -r requirements.txt
+          pip install -e .[dev]
 
       - name: Start ScienceBeam Docker container
         run: |
-          docker run -d --rm -p 8082:8070 elifesciences/sciencebeam-parser
+          docker run -d --rm -p 8070 elifesciences/sciencebeam-parser
 
       - name: Run tests
         run: |
-          tox
+          tox
+
+      - name: Test packaging
+        run: |
+          tox -e .package

.gitignore

@@ -1,4 +1,6 @@
 # Ignore the virtual environment directory
+_version.py
+node_modules
 venv/
 *coverage*
 .idea

.pre-commit-config.yaml

@@ -0,0 +1,35 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: 24.4.2
+    hooks:
+      - id: black
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: "v0.4.9"
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+        files: ".*\\.py"
+        exclude: "examples|docs/examples"
+      - id: check-added-large-files
+      - id: check-toml
+      - id: end-of-file-fixer
+        exclude: "examples|docs/examples"
+
+  # - repo: https://github.com/pre-commit/mirrors-prettier
+  #   rev: v4.0.0-alpha.8
+  #   hooks:
+  #     - id: prettier
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        name: isort
+        args: ["--profile", "black"]

README.md

@@ -8,10 +8,20 @@ OpenSciMetrics (OSM) applies NLP and LLM-based metrics and indicators related to
 Windows: `venv\Scripts\activate`<br>
 macOS and Linux: `source venv/bin/activate`
 
-- Next, run `pip install -r requirements.txt` to install all the dependencies.
-- Finally, run `python -m osm.cli pdf-xml "path_to_file_name.pdf" file_id`
+- Next, run `pip install -e .` to install the package with its dependencies.
+- Finally, run `osm pdf-xml "path_to_file_name.pdf" file_id`
 
 # How to run tests of the application
 Run `tox`
 # How to run the unit tests
-- Navigate to the project's root directory and run `python -m pytest`
+- Navigate to the project's root directory and run `pytest`
+
+# Using pre-commit for commit checks
+
+Pre-commit will run all of its hooks on every commit you make. To install
+pre-commit and its hooks, run the following commands:
+
+```
+pip install pre-commit
+pre-commit install
+```

osm_cli/__init__.py

@@ -0,0 +1,3 @@
+from . import _version
+
+__version__ = _version.version

osm_cli/cli/main.py

@@ -0,0 +1,18 @@
+import click
+
+from osm_cli.logging.logger import logger
+
+
+@click.group()
+def osm():
+    """Main command for OSM"""
+    pass
+
+
+@osm.command()
+@click.argument("file_path", type=click.Path(exists=True))
+@click.argument("file_id", type=str)
+def pdf_xml(file_path, file_id):
+    """This function converts a file from PDF to XML"""
+    # Function Implementation
+    logger.info(f"Converted: {file_path} with ID: {file_id} to XML")

logs/logger.py → osm_cli/logging/logger.py

@@ -1,11 +1,9 @@
-from rich.logging import RichHandler
 import logging
 
+from rich.logging import RichHandler
+
 logging.basicConfig(
-    level=logging.INFO,
-    format="%(message)s",
-    datefmt="[%X]",
-    handlers=[RichHandler()]
+    level=logging.INFO, format="%(message)s", datefmt="[%X]", handlers=[RichHandler()]
 )
 
 logger = logging.getLogger("rich")

osm_cli/utils/config.py

@@ -0,0 +1,10 @@
+from pydantic.v1 import BaseSettings
+
+
+class AppConfig(BaseSettings):
+    PORT: int = 8082
+    HOST: str = "localhost"
+    PROTOCAL: str = "http"
+
+
+config = AppConfig()

pyproject.toml

@@ -0,0 +1,55 @@
+[project]
+name = "osm-cli"
+description = "Open Science Metrics (OSM) client for tracking scientific transparency and reproducibility metrics"
+readme = "README.md"
+requires-python = ">=3.8"
+keywords = [
+  "open science",
+  "altmetrics",
+  "scientific transparency",
+  "reproducibility"
+]
+dynamic = ["version"]
+
+dependencies = [
+    "click>=8.1.7",
+    "rich>=13.7.1",
+]
+
+[project.optional-dependencies]
+dev = [
+    "tox>=4.15.0",
+    "pytest>=8.2.1",
+    "pytest-cov",
+    "ruff>=0.4.9",
+    "build",
+    "twine",
+    "pre-commit",
+    "pkginfo>=1.10"
+]
+
+[project.urls]
+homepage = "https://website"
+source = "https://github.com/nimh-dsst/osm-cli"
+issues = "https://github.com/nimh-dsst/osm-cli/issues"
+
+[build-system]
+requires = ["setuptools>=42", "wheel", "setuptools_scm[toml]>=3.4"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools_scm]
+write_to = "osm_cli/_version.py"
+
+[tool.setuptools.packages.find]
+where = ["osm_cli"]
+
+[project.scripts]
+osm-cli = "osm_cli.cli.main:osm"
+
+[tool.black]
+line-length = 88
+target-version = ["py38", "py39", "py310"]
+
+[tool.ruff]
+line-length = 88
+indent-width = 4

tests/test_file_processing.py

@@ -1,31 +1,22 @@
-import pytest
-from click.testing import CliRunner
-import os
 import logging
 
-from commands.file_processing import pdf_xml
+import pytest
+from click.testing import CliRunner
 
-@pytest.mark.usefixtures("caplog")
-class TestFileProcessing:
-    def setup_method(self):
-        # Create a temporary PDF file for testing
-        self.pdf_path = 'test_sample.pdf'
-        with open(self.pdf_path, 'wb') as f:
-            f.write(b'%PDF-1.4\n%Test PDF content\n')
+from osm_cli.cli.main import pdf_xml
 
-    def teardown_method(self):
-        # Remove the temporary PDF file and any generated XML file
-        if os.path.exists(self.pdf_path):
-            os.remove(self.pdf_path)
-        xml_output = f"{self.pdf_path.replace('.pdf', '')}_test_file.xml"
-        if os.path.exists(xml_output):
-            os.remove(xml_output)
 
-    def test_pdf_xml_command(self, caplog):
-        caplog.set_level(logging.INFO)
+@pytest.fixture
+def sample_pdf(tmp_path):
+    pdf_path = tmp_path / "test_sample.pdf"
+    pdf_path.write_bytes(b"%PDF-1.4\n%Test PDF content\n")
+    yield pdf_path
+    pdf_path.unlink()
 
-        runner = CliRunner()
-        result = runner.invoke(pdf_xml, [self.pdf_path, 'test_file'])
 
-        assert result.exit_code == 0
-        assert f'Converted: {self.pdf_path}' in caplog.text
+def test_pdf_converter(caplog, sample_pdf):
+    caplog.set_level(logging.INFO)
+    runner = CliRunner()
+    result = runner.invoke(pdf_xml, [str(sample_pdf), "test_file"])
+    assert result.exit_code == 0
+    assert f"Converted: {sample_pdf}" in caplog.text

tox.ini

@@ -1,20 +1,23 @@
 [tox]
-envlist = py39, py310, py311, py312, lint
+envlist = py39, py310, py311, py312, lint, format
 
 [testenv]
 deps =
-    pytest
-    pytest-cov
-    -r requirements.txt
+    .[dev]
 commands =
-    python -m pytest --cov=commands --cov-report=term-missing --cov-report=html --cov-report=xml
+    python -m pytest --cov=osm_cli --cov-report=term-missing --cov-report=html --cov-report=xml
 
 [testenv:lint]
 description = Run ruff to lint the code
 commands =
     ruff check .
 
 [testenv:format]
-description = Run ruff to format the code
+description = Check that code is formatted with ruff
 commands =
-    ruff check --fix .
+    ruff format --check
+
+[testenv:.package]
+description = Generate distribution package
+basepython = python3
+commands = python -m build --sdist --wheel --outdir packaged