Update project to use latest build tools and requirements, closes #13

.github/workflows/build.yml

@@ -14,7 +14,7 @@ jobs:
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v2
         with:
-          python-version: 3.8
+          python-version: 3.9
 
       - name: Install dependencies - Windows
         run: choco install wget
@@ -29,8 +29,11 @@ jobs:
         env:
           PYTHONUTF8: 1
 
+      - uses: pre-commit/[email protected]
+        if: matrix.os == 'ubuntu-latest'
+
       - name: Test Coverage
         run: coveralls --service=github
         if: matrix.os == 'ubuntu-latest'
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.pre-commit-config.yaml

@@ -0,0 +1,14 @@
+repos:
+  - repo: https://github.com/pycqa/pylint
+    rev: v3.3.1
+    hooks:
+    - id: pylint
+      args:
+      - -d import-error
+      - -d duplicate-code
+      - -d too-many-positional-arguments
+  - repo: https://github.com/ambv/black
+    rev: 24.10.0
+    hooks:
+    - id: black
+      language_version: python3

.pylintrc

@@ -15,6 +15,3 @@ min-public-methods=0
 
 [FORMAT]
 max-line-length=150
-
-[MESSAGES CONTROL]
-disable=I0011,R0201,W0105,W0108,W0110,W0141,W0621,W0640

README.md

@@ -31,7 +31,7 @@
 
 ![demo](https://raw.githubusercontent.com/neuml/txtmarker/master/demo.png)
 
-txtmarker highlights text in documents. txtmarker takes a list of (name, text) pairs, scan an input document and creates a modified version with highlights embedded.
+txtmarker highlights text in documents. txtmarker takes a list of (name, text) pairs, scans an input document and creates a modified version with highlights embedded.
 
 Current file formats supported:
 
@@ -40,13 +40,19 @@ Current file formats supported:
 ## Installation
 The easiest way to install is via pip and PyPI
 
-    pip install txtmarker
+```
+pip install txtmarker
+```
+
+Python 3.9+ is supported. Using a Python [virtual environment](https://docs.python.org/3/library/venv.html) is recommended.
 
-You can also install txtmarker directly from GitHub. Using a Python Virtual Environment is recommended.
+txtmarker can also be installed directly from GitHub to access the latest, unreleased features.
 
-    pip install git+https://github.com/neuml/txtmarker
+```
+pip install git+https://github.com/neuml/txtmarker
+```
 
-Python 3.8+ is supported
+Python 3.9+ is supported
 
 ## Examples
 

setup.py

@@ -1,34 +1,33 @@
 # pylint: disable = C0111
 from setuptools import find_packages, setup
 
-with open("README.md", "r") as f:
+with open("README.md", "r", encoding="utf-8") as f:
     DESCRIPTION = f.read()
 
-setup(name="txtmarker",
-      version="1.1.0",
-      author="NeuML",
-      description="Finds and highlights text in documents",
-      long_description=DESCRIPTION,
-      long_description_content_type="text/markdown",
-      url="https://github.com/neuml/txtmarker",
-      project_urls={
-          "Documentation": "https://github.com/neuml/txtmarker",
-          "Issue Tracker": "https://github.com/neuml/txtmarker/issues",
-          "Source Code": "https://github.com/neuml/txtmarker",
-      },
-      license="Apache 2.0: http://www.apache.org/licenses/LICENSE-2.0",
-      packages=find_packages(where="src/python"),
-      package_dir={"": "src/python"},
-      keywords="pdf highlight text search",
-      python_requires=">=3.8",
-      install_requires=[
-          "pdfminer.six>=20201018",
-          "pdf-annotate>=0.11.0"
-      ],
-      classifiers=[
-          "License :: OSI Approved :: Apache Software License",
-          "Operating System :: OS Independent",
-          "Programming Language :: Python :: 3",
-          "Topic :: Software Development",
-          "Topic :: Utilities"
-      ])
+setup(
+    name="txtmarker",
+    version="1.1.0",
+    author="NeuML",
+    description="Finds and highlights text in documents",
+    long_description=DESCRIPTION,
+    long_description_content_type="text/markdown",
+    url="https://github.com/neuml/txtmarker",
+    project_urls={
+        "Documentation": "https://github.com/neuml/txtmarker",
+        "Issue Tracker": "https://github.com/neuml/txtmarker/issues",
+        "Source Code": "https://github.com/neuml/txtmarker",
+    },
+    license="Apache 2.0: http://www.apache.org/licenses/LICENSE-2.0",
+    packages=find_packages(where="src/python"),
+    package_dir={"": "src/python"},
+    keywords="pdf highlight text search",
+    python_requires=">=3.9",
+    install_requires=["pdfminer.six>=20201018", "pdf-annotate>=0.11.0"],
+    classifiers=[
+        "License :: OSI Approved :: Apache Software License",
+        "Operating System :: OS Independent",
+        "Programming Language :: Python :: 3",
+        "Topic :: Software Development",
+        "Topic :: Utilities",
+    ],
+)