Merge pull request #22 from SamEdwardes/feature/python3.12

Add support for Python 3.12

.github/workflows/pytest.yml

@@ -7,7 +7,7 @@ on:
   pull_request:
     branches: [ main ]
   push:
-    branches: 
+    branches:
       - main
   workflow_dispatch:
 
@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v2
@@ -29,13 +29,9 @@ jobs:
       run: |
         sudo apt-get update
         sudo apt-get install -y poppler-utils tesseract-ocr libtesseract-dev
-    - name: Setup poetry
+    - name: Setup uv
       run: |
-        python -m pip install --upgrade pip wheel setuptools
-        curl -sSL https://install.python-poetry.org | python3 -
-    - name: Install dependencies
-      run: |
-        poetry install --all-extras
+        curl -LsSf https://astral.sh/uv/install.sh | sh
     - name: Test with pytest
       run: |
-        poetry run pytest
+        uv run --python ${{ matrix.python-version }} --all-extras pytest

docs/changelog.md

@@ -1,5 +1,18 @@
 # Changelog
 
+## 0.3.2 (2024-10-04)
+
+**Changes**
+
+- Support for Python 3.8 to 3.12 and all future 3.0 versions of Python ([#16](https://github.com/SamEdwardes/spacypdfreader/issues/16), [#21](https://github.com/SamEdwardes/spacypdfreader/issues/21))
+- Added local testing to test matrix of supported Python versions.
+- Switch from poetry to uv for managing project dependencies and building project.
+- Update dependencies.
+
+**Fixes**
+
+None
+
 ## 0.3.1 (2023-10-17)
 
 **Changes**

docs/contributing.md

@@ -6,7 +6,13 @@ Before merging changes into main the following must be completed:
 
 - [ ] Bump the version number in *pyproject.toml* and *spacypdfreader.__init__.py*
 - [ ] Format the code: `just format`
-- [ ] Run pytest: `just test`
+- [ ] Run pytest:
+
+    ```bash
+    just test-matrix
+    just test-docs
+    ```
+- Test publishing to test PyPI: `just publish-test`
 - [ ] Check the docs locally: `just preview-docs`
 
 After merging the pull request:
@@ -17,7 +23,7 @@ After merging the pull request:
 
 ## Code style
 
-The black code formatter should be run against all code.
+The ruff code formatter should be run against all code.
 
 ```bash
 just format

justfile

@@ -1,25 +1,66 @@
+default:
+    @just --list
+
+[group('package')]
+build:
+    rm -rf dist
+    uv build
+
+[group('package')]
+publish-test:
+    rm -rf dist
+    uv build
+    uv publish --token $(op read "op://Private/Test PyPI/Token") --publish-url https://test.pypi.org/legacy/
+    open https://test.pypi.org/project/spacypdfreader/
+
+[group('package')]
+publish:
+    rm -rf dist
+    uv build
+    uv publish --token $(op read "op://Private/PyPI/Token")
+    open https://pypi.org/project/spacypdfreader/
+
+[group('lint')]
 format:
-    # Source code
-    poetry run black spacypdfreader
-    poetry run isort spacypdfreader
-    # Tests
-    poetry run black tests
-    poetry run isort tests
+    # Sort imports
+    uvx ruff check --select I --fix .
+    # Format code
+    uvx ruff format .
 
-test:
-    poetry run pytest
-    poetry run pytest --doctest-modules spacypdfreader/
+[group('lint')]
+lint:
+    uvx ruff check .
 
+[group('tests')]
+test version="3.12":
+    uv run --python {{version}} --all-extras pytest
+
+[group('tests')]
+test-matrix:
+    just test 3.9
+    just test 3.10
+    just test 3.11
+    just test 3.12
+
+[group('tests')]
+test-pre-release-python:
+    # As of 2024-10-04 3.13 is failing
+    just test 3.13
+
+[group('tests')]
 test-gha:
     gh workflow run pytest.yml --ref $(git branch --show-current)
 
+[group('docs')]
 preview-docs:
-    poetry run mkdocs serve
+    uv run mkdocs serve
 
+[group('docs')]
 publish-docs:
     rm -rf site
-    mkdocs build
-    mkdocs gh-deploy
+    uv run mkdocs build
+    uv run mkdocs gh-deploy
 
-publish:
-    poetry publish --build
+[group('docs')]
+test-docs:
+    uv run --python 3.12 --all-extras pytest --doctest-modules spacypdfreader/

notebooks/spacypdfreader-demo.ipynb

@@ -8,9 +8,10 @@
    "outputs": [],
    "source": [
     "import spacy\n",
+    "\n",
     "from spacypdfreader import pdf_reader\n",
-    "from spacypdfreader.parsers.pytesseract import PytesseractParser\n",
-    "from spacypdfreader.parsers.pdfminer import PdfminerParser"
+    "from spacypdfreader.parsers.pdfminer import PdfminerParser\n",
+    "from spacypdfreader.parsers.pytesseract import PytesseractParser"
    ]
   },
   {

pyproject.toml

@@ -1,36 +1,48 @@
-[tool.poetry]
+[project]
 name = "spacypdfreader"
-version = "0.3.1"
+version = "0.3.2"
 description = "A PDF to text extraction pipeline component for spaCy."
-authors = ["SamEdwardes <[email protected]>"]
 license = "MIT"
 readme = "README.md"
-repository = "https://github.com/SamEdwardes/spaCyPDFreader"
+maintainers = [
+  {name = "Sam Edwardes", email = "[email protected]"}
+]
 keywords = ["python", "spacy", "nlp", "pdf", "pdfs"]
+requires-python = ">=3.9"
+dependencies = [
+    "pdfminer-six>=20240706",
+    "rich>=13.9.2",
+    "spacy>=3.8.2",
+]
 
-[tool.poetry.dependencies]
-python = ">=3.8,<3.12"
-spacy = "^3.4"
-rich = "^10.15.2"
-"pdfminer.six" = "^20211012"
-pytesseract = {version = "^0.3.8", optional = true}
-pdf2image = {version = "^1.16.0", optional = true}
-numpy = "^1.24.2"
-Pillow = {version = "^9.4.0", optional = true}
+[project.urls]
+Homepage = "https://samedwardes.github.io/spacypdfreader"
+Documentation = "https://samedwardes.github.io/spacypdfreader"
+Repository = "https://github.com/SamEdwardes/spaCyPDFreader.git"
+Issues = "https://github.com/SamEdwardes/spaCyPDFreader/issues"
+Changelog = "https://github.com/SamEdwardes/spacypdfreader/blob/main/docs/changelog.md"
 
-[tool.poetry.extras]
-pytesseract = ["pytesseract", "Pillow", "pdf2image"]
-
-[tool.poetry.group.dev.dependencies]
-pytest = "^6.2.5"
-en-core-web-sm = {url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.1/en_core_web_sm-3.4.1-py3-none-any.whl"}
-mkdocs-material = "^9.1.1"
-mkdocs-include-markdown-plugin = "^4.0.3"
-mkdocstrings = {extras = ["python"], version = "^0.20.0"}
-ipykernel = "^6.25.2"
-black = "^23.9.1"
-isort = "^5.12.0"
+[project.optional-dependencies]
+pytesseract = [
+    "pdf2image>=1.17.0",
+    "pillow>=10.4.0",
+    "pytesseract>=0.3.13",
+]
 
 [build-system]
-requires = ["poetry-core>=1.0.0"]
-build-backend = "poetry.core.masonry.api"
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.uv]
+dev-dependencies = [
+    "mkdocs>=1.6.1",
+    "mkdocs-include-markdown-plugin>=6.2.2",
+    "mkdocs-material>=9.5.39",
+    "pytest>=8.3.3",
+    "en-core-web-sm",
+    "mkdocstrings>=0.26.1",
+    "mkdocstrings-python>=1.11.1",
+]
+
+[tool.uv.sources]
+en-core-web-sm = { url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl" }

tests/test_spacypdfreader.py

@@ -3,7 +3,7 @@
 
 
 def test_version():
-    assert __version__ == "0.3.1"
+    assert __version__ == "0.3.2"
 
 
 def test_get_number_of_pages():