Merge pull request #377 from chartbeat-labs/develop

v0.13 release

.github/workflows/checks.yml

@@ -0,0 +1,78 @@
+name: checks
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:  # run on all PRs
+  schedule:  # run weekly
+    - cron: "0 12 * * 0"
+
+jobs:
+
+  tests:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.10", "3.11"]
+        os: [macos-latest, ubuntu-latest, windows-latest]
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+        cache: "pip"
+        cache-dependency-path: "pyproject.toml"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip wheel
+        python -m pip install -e '.[check]'
+    - name: Download language data
+      run: |
+        make download
+    - name: Test with pytest
+      run: |
+        python -m pytest tests --verbose --cov=textacy --cov-report=term-missing
+
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.9"
+        cache: "pip"
+        cache-dependency-path: "pyproject.toml"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip wheel
+        python -m pip install -e '.[check]'
+    - name: Check formatting with black
+      run: |
+        python -m black --diff src
+    - name: Check imports with isort
+      run: |
+        python -m isort --diff src
+    - name: Check correctness with ruff
+      run: |
+        python -m ruff check --exit-zero src
+
+  types:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.9"
+        cache: "pip"
+        cache-dependency-path: "pyproject.toml"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip wheel
+        python -m pip install -e '.[check]'
+    - name: Check types with mypy
+      run: |
+        python -m mypy --install-types --non-interactive src

.github/workflows/docs.yml

@@ -1,38 +1,27 @@
 name: docs
 
 on:
-  push:  # run on every push to default branch
-    branches: [ $default-branch, main ]
-  pull_request:  # run on all pull requests
+  push:
+    branches: [ main, develop ]
 
 jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        build-type: [ html, text ]
-
+        build-type: [html, text]
     steps:
-    - uses: actions/checkout@v2
-    - name: set up Python
-      uses: actions/setup-python@v2
-      with:
-        python-version: 3.8
-    - name: get pip cache dir
-      id: pip-cache
-      run: |
-        echo "::set-output name=dir::$(pip cache dir)"
-    - name: set up pip cache
-      uses: actions/cache@v2
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v4
       with:
-        path: ${{ steps.pip-cache.outputs.dir }}
-        key: ${{ matrix.os }}-pip-${{ hashFiles('setup.cfg') }}
-        restore-keys: |
-          ${{ matrix.os }}-pip-
-    - name: install package and dependencies
+        python-version: "3.9"
+        cache: "pip"
+        cache-dependency-path: "pyproject.toml"
+    - name: Install dependencies
       run: |
         python -m pip install --upgrade pip wheel
-        python -m pip install -e .[docs]
+        python -m pip install -e '.[docs]'
     - name: make ${{ matrix.build-type }} docs
       run: |
         cd docs && make ${{ matrix.build-type }}

.github/workflows/publish.yml

@@ -0,0 +1,37 @@
+name: publish
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.9"
+        cache: "pip"
+        cache-dependency-path: "pyproject.toml"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build wheel
+    - name: Build package
+      run: |
+        python -m build --sdist --wheel
+    - name: Publish package to TestPyPI
+      uses: pypa/gh-action-pypi-publish@release/v1.6
+      with:
+        user: __token__
+        password: ${{ secrets.TEST_PYPI_API_TOKEN_BURTON }}
+        repository_url: https://test.pypi.org/legacy/
+    - name: Publish package to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1.6
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN_BURTON }}
+        verify_metadata: true
+        verbose: true

.gitignore

@@ -67,6 +67,9 @@ venv.bak/
 .dmypy.json
 dmypy.json
 
+# ruff
+.ruff_cache/
+
 # textacy
 data/
 

.readthedocs.yml

@@ -4,7 +4,7 @@
 version: 2
 
 python:
-  version: 3.8
+  version: 3.9
   install:
     - method: pip
       path: .

CHANGES.md

@@ -1,5 +1,28 @@
 ## Changes
 
+### 0.13.0 (2023-04-02)
+
+- upgraded built-in language identification model (PR #375)
+  - replaced v2 thinc/cld3 model with v3 floret/fasttext model, which has much faster predictions and comparable but more consistent performance
+- modernized and improved Python packaging for faster, simpler installation and testing (PR #368 and #369)
+  - all package metadata and configuration moved into a single `pyproject.toml` file
+  - code formatting and linting updated to use `ruff` plus newer versions of `mypy` and `black`, and their use in GitHub Actions CI has been consolidated
+  - bumped supported Python versions range from 3.8–3.10 to 3.9–3.11 (PR #369)
+  - added full CI testing matrix for PY 3.9/3.10/3.11 x Linux/macOS/Windows, and removed extraneous AppVeyor integration
+- updated and improved type hints throughout, reducing number of `mypy` complaints by ~80% (PR #372)
+
+#### Fixed
+
+- fixed ReDoS bugs in regex patterns (PR #371)
+- fixed breaking API issues with newer networkx/scikit-learn versions (PR #367)
+- improved dev workflow documentation and code to better incorporate language data (PR #363)
+- updated caching code with a fix from upstream pysize library, which was preventing Russian-language spaCy model from loading properly (PR #358)
+
+#### Contributors
+
+Big thanks to @jonwiggins, @Hironsan, amnd @kevinbackhouse for the fixes!
+
+
 ### 0.12.0 (2021-12-06)
 
 - Refactored and extended text statistics functionality (PR #350)
@@ -43,6 +66,7 @@
 
 Thanks to @austinjp, @scarroll32, @MirkoLenz for their help!
 
+
 ### 0.11.0 (2021-04-12)
 
 - **Refactored, standardized, and extended several areas of functionality**

CONTRIBUTING.md

@@ -47,11 +47,12 @@ Use an appropriate template (if available) when [creating your issue](https://gi
 
 1. **Implement your changes:** Use your preferred text editor to modify the `textacy` source code. Be sure to keep your changes focused and in scope, and follow the coding conventions described below! Document your code as you write it. Run your changes against any existing tests and add new ones as needed to validate your changes; make sure you don’t accidentally break existing functionality! Several common commands can be accessed via the package `Makefile`:
 
-        $ make test
-        $ make lint
-        $ make mypy
+        $ make download
+        $ make check-tests
+        $ make check-lint
+        $ make check-types
 
-    Or, to run all three at once, use
+    Or, to run the latter three steps at once, use
 
         $ make check
 

MANIFEST.in

@@ -2,6 +2,7 @@ graft src
 graft scripts
 graft tests
 graft docs
+prune src/textacy/data/
 prune docs/build/
 
 include CHANGES.md

Makefile

@@ -1,4 +1,4 @@
-.PHONY: clean-build clean-py clean-test clean test lint check-types
+.PHONY: clean-build clean-py clean-test clean check-tests check-lint check-types check build download
 
 clean-build:
 	rm -rf dist build .egg .eggs **/*.egg-info
@@ -13,16 +13,25 @@ clean-test:
 
 clean: clean-build clean-py clean-test
 
-build: clean-build
-	python -m build --sdist --wheel
+check-tests: clean-test
+	python -m pytest tests --verbose --cov=textacy --cov-report=term-missing
 
-test: clean-test
-	python -m pytest tests -v --cov=textacy --cov-report=term-missing
+check-lint:
+	python -m black --diff src
+	python -m isort --diff src
+	python -m ruff check src
 
-lint:
-	python -m flake8 src
-
-mypy:
+check-types:
 	python -m mypy src
 
-check: test lint mypy
+check: check-tests check-lint check-types
+
+build: clean-build
+	python -m build --sdist --wheel
+
+download:
+	python -m spacy download en_core_web_sm
+	python -m spacy download es_core_news_sm
+	python -m spacy validate
+	python -m textacy download capitol_words
+	python -m textacy download lang_identifier --version 3.0