Improve dev experience (#38)

* Improve dev experience

* Add pytest and flake8 commands to readme

* Use --filename in flake8

* Lint all py files

* Add Makefile and update readme

* Lint

.github/workflows/pythonpackage.yml

@@ -21,22 +21,16 @@ jobs:
       uses: actions/setup-python@v1
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
+    - name: Install package and dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install -r requirements.txt
+        pip install .[dev]
     - name: Lint with flake8
       run: |
-        pip install flake8
         # stop the build if there are Python syntax errors or undefined names
-        flake8 **/*.py --count --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 **/*.py --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Install package
-      run: |
-        # required because of entry points
-        pip install .
+        flake8 --filename=*.py --count --show-source --max-line-length=119 --statistics
+        # exit-zero treats all errors as warnings
+        flake8 --filename=*.py --count --exit-zero --max-line-length=119 --max-complexity=10 --statistics
     - name: Test with pytest
       run: |
-        pip install pytest
         python -m pytest -vvv tests

.gitignore

@@ -1,3 +1,6 @@
+# Ignore models dir
+spacy_udpipe/models
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

Makefile

@@ -0,0 +1,14 @@
+.PHONY: lint test
+
+# Lint source code
+
+lint:
+	# stop the build if there are Python syntax errors or undefined names
+	flake8 --filename=*.py --count --show-source --max-line-length=119 --statistics
+	# exit-zero treats all errors as warnings
+	flake8 --filename=*.py --count --exit-zero --max-line-length=119 --max-complexity=10 --statistics
+
+# Run tests
+
+test:
+	python -m pytest -vvv tests

README.md

@@ -61,7 +61,14 @@ This can be done for any of the languages supported by spaCy. For an exhaustive
 Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
 
 Please make sure to update the tests as appropriate. Tests are run automatically for each pull request on the master branch.
-To start the tests locally, first, install the package with `pip install -e .`, then run [`pytest`](https://docs.pytest.org/en/latest/contents.html) in the root source directory.
+To start the tests locally, first, install the package with `pip install -e .[dev]`, then run [`pytest`](https://docs.pytest.org/en/latest/contents.html) in the root source directory as follows:
+```bash
+make test
+```
+Additionally, run [`flake8`](https://flake8.pycqa.org/en/latest) with the following command to check for coding mistakes:
+```bash
+make lint
+```
 
 ## License
 * Source code: [MIT](https://choosealicense.com/licenses/mit/) © Text Analysis and Knowledge Engineering Lab (TakeLab)

setup.py

@@ -1,6 +1,6 @@
 import os
 
-import setuptools
+from setuptools import find_packages, setup
 
 
 def get_version(fname: str) -> str:
@@ -9,11 +9,11 @@ def get_version(fname: str) -> str:
         "spacy_udpipe",
         fname
     )
-    with open(full_path, "r") as fp:
-        for l in fp:
-            if l.startswith("__version__"):
-                delim = '"' if '"' in l else "'"
-                return l.split(delim)[1]
+    with open(full_path, "r", encoding="utf-8") as fp:
+        for line in fp:
+            if line.startswith("__version__"):
+                delim = '"' if '"' in line else "'"
+                return line.split(delim)[1]
             else:
                 raise RuntimeError(
                     "Unable to find version string."
@@ -22,10 +22,10 @@ def get_version(fname: str) -> str:
 
 URL = "https://github.com/TakeLab/spacy-udpipe"
 
-with open("README.md", "r") as f:
+with open("README.md", "r", encoding="utf-8") as f:
     readme = f.read()
 
-setuptools.setup(
+setup(
     name="spacy_udpipe",
     version=get_version("__init__.py"),
     description="Use fast UDPipe models directly in spaCy",
@@ -36,8 +36,11 @@ def get_version(fname: str) -> str:
     author_email="[email protected]",
     license="MIT",
     keywords="nlp udpipe spacy python",
-    packages=setuptools.find_packages(),
+    packages=find_packages(),
     install_requires=["spacy>=3.0.0,<4.0.0", "ufal.udpipe>=1.2.0"],
+    extras_require={
+        "dev": ["flake8", "pytest"],
+    },
     python_requires=">=3.6",
     entry_points={
         "spacy_tokenizers": [
@@ -49,9 +52,15 @@ def get_version(fname: str) -> str:
     classifiers=[
         "Development Status :: 4 - Beta",
         "Intended Audience :: Developers",
+        "Intended Audience :: Education",
+        "Intended Audience :: Science/Research"
         "Programming Language :: Python :: 3",
         "License :: OSI Approved :: MIT License",
         "Operating System :: OS Independent",
+        "Topic :: Software Development",
+        "Topic :: Software Development :: Libraries",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+        "Topic :: Text Processing",
     ],
     project_urls={
         "SpaCy": "https://spacy.io/",

spacy_udpipe/utils.py

@@ -10,10 +10,7 @@
 BASE_URL = "https://lindat.mff.cuni.cz/repository/xmlui/bitstream/handle/11234/1-3131"  # noqa: E501
 MODELS_DIR = os.path.join(os.path.dirname(__file__), "models")
 with open(
-    os.path.join(
-        os.path.dirname(__file__),
-        "languages.json"
-    ),
+    os.path.join(os.path.dirname(__file__), "languages.json"), encoding="utf-8"
 ) as f:
     LANGUAGES = json.load(f)
 

tests/languages/fr/test_fr_language.py

@@ -1,5 +1,3 @@
-from typing import List
-
 import pytest
 from spacy.lang.fr import FrenchDefaults
 from spacy.language import BaseDefaults
@@ -24,12 +22,12 @@ def test_get_defaults(lang: str) -> None:
 
 def test_spacy_udpipe(lang: str) -> None:
     nlp = load(lang=lang)
-    
+
     text = "Attention aux articles contractés!"
-    doc = nlp (text=text)
-    
+    doc = nlp(text=text)
+
     assert [t.orth_ for t in doc] == ["Attention", "à", "les", "articles", "contractés", "!"]
-    
+
     pos = [{"INTJ", "NOUN"}, {"ADP"}, {"DET"}, {"NOUN"}, {"VERB", "ADJ"}, {"PUNCT"}]
     for i, t in enumerate(doc):
         assert t.pos_ in pos[i]