From e2ca88c2470d0748fe29235bad144aba5c60ec30 Mon Sep 17 00:00:00 2001 From: surtur Date: Mon, 20 Dec 2021 04:57:48 +0100 Subject: [PATCH] feat: make this project a module * update .gitignore * add __init__.py * add main.py * add test strings of both smaller and greater size * call what_this method with test strings as parameters * call what_this without the text parameter to demonstrate there is a fallback --- .gitignore | 140 ++++++++++++++++++++++++++++++++++++++++++++++++++++ __init__.py | 0 main.py | 45 +++++++++++++++++ 3 files changed, 185 insertions(+) create mode 100644 __init__.py create mode 100755 main.py diff --git a/.gitignore b/.gitignore index f3f2cc2..9a7345c 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,142 @@ *.swp freqs/ + +### Python ### +# 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 + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow +__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/ diff --git a/__init__.py b/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/main.py b/main.py new file mode 100755 index 0000000..5f09fb9 --- /dev/null +++ b/main.py @@ -0,0 +1,45 @@ +#!/usr/bin/env python3 +""" +this file is part of the da_detector NLP project +""" + + +import da_detector as detector + + +test_str = "what freaking ever, nobody cares one bit of a heck" +test_str_sk = "Nad Tatrou sa blýska, hromy divo bijú." +test_str_sk_long = """1. Nad Tatrou sa blýska +hromy divo bijú, +nad Tatrou sa blýska +hromy divo bijú, +Zastavme ich, bratia, +veď sa ony stratia, +Slováci ožijú. +2. To Slovensko naše +posiaľ tvrdo spalo, +ale blesky hromu +vzbudzujú ho k tomu, +aby sa prebralo. +3. Ešte jedle rastú +na krivánskej strane +Kto jak Slovák cíti, +nech sa šable chytí, +a medzi nás stane. +4. Už Slovensko vstáva, +putá si strháva +Hej rodina milá +hodina odbila, +žije matka Sláva!""" + +all_langs = ["sk", "cz", "de", "en", "fr"] + + +d = detector.da_detector() + +d.what_this(test_str, ["sk", "de", "en"]) +d.what_this(test_str, []) +d.what_this(test_str_sk, []) +d.what_this(test_str_sk_long, all_langs) + +# vim: ff=unix noexpandtab