Updated module to Unicode 15.1

.github/workflows/pylint.yml

@@ -0,0 +1,27 @@
+name: Pylint
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10"]
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pylint
+    - name: Analysing the code with pylint
+      run: |
+        pylint $(git ls-files '*.py')

.github/workflows/python-package.yml

@@ -0,0 +1,40 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Python package
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8 pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        pytest --doctest-modules

.gitignore

@@ -1,9 +1,160 @@
-__pycache__
-doc
-update/PropertyValueAliases.txt
-update/ScriptExtensions.txt
-update/Scripts.txt
-dist
-*.egg-info
-build
-files.txt
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -1,41 +1,90 @@
+[![Pylint](https://github.com/gaspardpetit/uniscripts/actions/workflows/pylint.yml/badge.svg)](https://github.com/gaspardpetit/uniscripts/actions/workflows/pylint.yml)
+[![Python package](https://github.com/gaspardpetit/uniscripts/actions/workflows/python-package.yml/badge.svg)](https://github.com/gaspardpetit/uniscripts/actions/workflows/python-package.yml)
+[![PyPI version](https://badge.fury.io/py/uniscripts.svg)](https://pypi.python.org/pypi/uniscripts/)
+[![Python versions](https://img.shields.io/pypi/pyversions/uniscripts.svg)](https://pypi.org/project/uniscripts/)
+[![Unicode versions](https://img.shields.io/badge/Unicode%20-15.1-blue.svg)](https://www.unicode.org/charts/)
+[![License: CC0-1.0](https://img.shields.io/badge/License-CC0_1.0-lightgrey.svg)](http://creativecommons.org/publicdomain/zero/1.0/)
+
+# Uniscripts
+
 Simple Python 3 module to query Unicode UCD script metadata (see UAX #24).
 
 This module is useful for querying if a text is made of Latin characters,
 Arabic, hiragana, kanji (han), and so on.  It works for all scripts supported
 by the Unicode character database.
 
-This module is dumb and slow.  If you need speed, you probably want to
-implement your own functions.  See e.g. `man pcreunicode`, `man pcrepattern`
-(`grep -P` supports `\p`).  As of this writing, the next-generation of Python
-regexpes, available as the pypi library `regex`, also supports `\p`.
-
 Sample usage:
 
-    >>> import uniscripts
-    >>> uniscripts.is_script('A', 'Latin')
-    True
+### Verify is a string is of a given script:
+
+```python
+>>> from uniscripts import is_script, Scripts
+
+>>> is_script('A', Scripts.LATIN)
+True
+
+# if you pass it a string, all characters must match
+>>> is_script('はるはあけぼの', Scripts.HIRAGANA)
+True
+
+>>> is_script('はるはAkebono', Scripts.HIRAGANA)
+False
+
+# ...but by default, it ignores 'Common' characters, such as punctuation.
+>>> is_script('はるは:あけぼの', Scripts.HIRAGANA)
+True
+
+>>> is_script('中華人民共和国', Scripts.HAN) # 'Han' = kanji or hànzì
+True
+
+```
+See docstrings for `is_script()`.
+
+
+### Detect the script of a character:
+
+```python
+>>> from uniscripts import which_scripts
+
+>>> which_scripts('z')
+['Latin']
+
+>>> which_scripts('は')
+['Hiragana']
+
+>>> which_scripts('ー') # U+30FC
+['Bopomofo', 'Common', 'Han', 'Hangul', 'Hiragana', 'Katakana', 'Yi']
+
+```
+See docstrings for `is_script()`.
+
+
+### Detect the script of a text
+
+```python
+>>> from uniscripts import get_scripts
+>>> sorted(get_scripts("こんにちは"))
+['Hiragana']
+
+>>> sorted(get_scripts("チョコレート"))
+['Bopomofo', 'Common', 'Han', 'Hangul', 'Hiragana', 'Katakana', 'Yi']
 
-    # if you pass it a string, all characters must match
-    >>> uniscripts.is_script('はるはあけぼの', 'Hiragana')
-    True
+>>> sorted(get_scripts("ਚਾਕਲੇਟ"))
+['Gurmukhi']
 
-    >>> uniscripts.is_script('はるはAkebono', 'Hiragana')
-    False
+>>> sorted(get_scripts("초콜릿"))
+['Hangul']
 
-    # ...but by default, it ignores 'Common' characters, such as punctuation.
-    >>> uniscripts.is_script('はるは:あけぼの', 'Hiragana')
-    True
+>>> sorted(get_scripts("σοκολάτα"))
+['Greek']
 
-    >>> uniscripts.is_script('中華人民共和国', 'Han') # 'Han' = kanji or hànzì
-    True
+>>> sorted(get_scripts("شوكولاتة"))
+['Arabic']
 
-    >>> uniscripts.which_scripts('z')
-    ['Latin']
+>>> sorted(get_scripts("chocolat"))
+['Common', 'Latin']
 
-    >>> uniscripts.which_scripts('は')
-    ['Hiragana']
+```
 
-    >>> uniscripts.which_scripts('ー') # U+30FC
-    ['Common', 'Katakana', 'Hiragana', 'Hangul', 'Han', 'Bopomofo', 'Yi']
+See docstrings for `get_scripts()`.
 
-See docstrings for `is_script()`, `which_scripts()`.