mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-12 10:16:27 +03:00
58bdd8607b
* Edited Slovenian stop words list (#9707) * Noun chunks for Italian (#9662) * added it vocab * copied portuguese * added possessive determiner * added conjed Nps * added nmoded Nps * test misc * more examples * fixed typo * fixed parenth * fixed comma * comma fix * added syntax iters * fix some index problems * fixed index * corrected heads for test case * fixed tets case * fixed determiner gender * cleaned left over * added example with apostophe * French NP review (#9667) * adapted from pt * added basic tests * added fr vocab * fixed noun chunks * more examples * typo fix * changed naming * changed the naming * typo fix * Add Japanese kana characters to default exceptions (fix #9693) (#9742) This includes the main kana, or phonetic characters, used in Japanese. There are some supplemental kana blocks in Unicode outside the BMP that could also be included, but because their actual use is rare I omitted them for now, but maybe they should be added. The omitted blocks are: - Kana Supplement - Kana Extended (A and B) - Small Kana Extension * Remove NER words from stop words in Norwegian (#9820) Default stop words in Norwegian bokmål (nb) in Spacy contain important entities, e.g. France, Germany, Russia, Sweden and USA, police district, important units of time, e.g. months and days of the week, and organisations. Nobody expects their presence among the default stop words. There is a danger of users complying with the general recommendation of filtering out stop words, while being unaware of filtering out important entities from their data. See explanation in https://github.com/explosion/spaCy/issues/3052#issuecomment-986756711 and comment https://github.com/explosion/spaCy/issues/3052#issuecomment-986951831 * Bump sudachipy version * Update sudachipy versions * Bump versions Bumping to the most recent dictionary just to keep thing current. Bumping sudachipy to 5.2 because older versions don't support recent dictionaries. Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: Richard Hudson <richard@explosion.ai> Co-authored-by: Duygu Altinok <duygu@explosion.ai> Co-authored-by: Haakon Meland Eriksen <haakon.eriksen@far.no>
144 lines
3.4 KiB
INI
144 lines
3.4 KiB
INI
[metadata]
|
|
description = Industrial-strength Natural Language Processing (NLP) in Python
|
|
url = https://spacy.io
|
|
author = Explosion
|
|
author_email = contact@explosion.ai
|
|
license = MIT
|
|
long_description = file: README.md
|
|
long_description_content_type = text/markdown
|
|
classifiers =
|
|
Development Status :: 5 - Production/Stable
|
|
Environment :: Console
|
|
Intended Audience :: Developers
|
|
Intended Audience :: Science/Research
|
|
License :: OSI Approved :: MIT License
|
|
Operating System :: POSIX :: Linux
|
|
Operating System :: MacOS :: MacOS X
|
|
Operating System :: Microsoft :: Windows
|
|
Programming Language :: Cython
|
|
Programming Language :: Python :: 3
|
|
Programming Language :: Python :: 3.6
|
|
Programming Language :: Python :: 3.7
|
|
Programming Language :: Python :: 3.8
|
|
Programming Language :: Python :: 3.9
|
|
Programming Language :: Python :: 3.10
|
|
Topic :: Scientific/Engineering
|
|
project_urls =
|
|
Release notes = https://github.com/explosion/spaCy/releases
|
|
Source = https://github.com/explosion/spaCy
|
|
|
|
[options]
|
|
zip_safe = false
|
|
include_package_data = true
|
|
python_requires = >=3.6
|
|
setup_requires =
|
|
cython>=0.25,<3.0
|
|
numpy>=1.15.0
|
|
# We also need our Cython packages here to compile against
|
|
cymem>=2.0.2,<2.1.0
|
|
preshed>=3.0.2,<3.1.0
|
|
murmurhash>=0.28.0,<1.1.0
|
|
thinc>=8.0.12,<8.1.0
|
|
install_requires =
|
|
# Our libraries
|
|
spacy-legacy>=3.0.8,<3.1.0
|
|
spacy-loggers>=1.0.0,<2.0.0
|
|
murmurhash>=0.28.0,<1.1.0
|
|
cymem>=2.0.2,<2.1.0
|
|
preshed>=3.0.2,<3.1.0
|
|
thinc>=8.0.12,<8.1.0
|
|
blis>=0.4.0,<0.8.0
|
|
wasabi>=0.8.1,<1.1.0
|
|
srsly>=2.4.1,<3.0.0
|
|
catalogue>=2.0.6,<2.1.0
|
|
typer>=0.3.0,<0.5.0
|
|
pathy>=0.3.5
|
|
# Third-party dependencies
|
|
tqdm>=4.38.0,<5.0.0
|
|
numpy>=1.15.0
|
|
requests>=2.13.0,<3.0.0
|
|
pydantic>=1.7.4,!=1.8,!=1.8.1,<1.9.0
|
|
jinja2
|
|
# Official Python utilities
|
|
setuptools
|
|
packaging>=20.0
|
|
typing_extensions>=3.7.4,<4.0.0.0; python_version < "3.8"
|
|
langcodes>=3.2.0,<4.0.0
|
|
|
|
[options.entry_points]
|
|
console_scripts =
|
|
spacy = spacy.cli:setup_cli
|
|
|
|
[options.extras_require]
|
|
lookups =
|
|
spacy_lookups_data>=1.0.3,<1.1.0
|
|
transformers =
|
|
spacy_transformers>=1.1.2,<1.2.0
|
|
ray =
|
|
spacy_ray>=0.1.0,<1.0.0
|
|
cuda =
|
|
cupy>=5.0.0b4,<11.0.0
|
|
cuda80 =
|
|
cupy-cuda80>=5.0.0b4,<11.0.0
|
|
cuda90 =
|
|
cupy-cuda90>=5.0.0b4,<11.0.0
|
|
cuda91 =
|
|
cupy-cuda91>=5.0.0b4,<11.0.0
|
|
cuda92 =
|
|
cupy-cuda92>=5.0.0b4,<11.0.0
|
|
cuda100 =
|
|
cupy-cuda100>=5.0.0b4,<11.0.0
|
|
cuda101 =
|
|
cupy-cuda101>=5.0.0b4,<11.0.0
|
|
cuda102 =
|
|
cupy-cuda102>=5.0.0b4,<11.0.0
|
|
cuda110 =
|
|
cupy-cuda110>=5.0.0b4,<11.0.0
|
|
cuda111 =
|
|
cupy-cuda111>=5.0.0b4,<11.0.0
|
|
cuda112 =
|
|
cupy-cuda112>=5.0.0b4,<11.0.0
|
|
cuda113 =
|
|
cupy-cuda113>=5.0.0b4,<11.0.0
|
|
cuda114 =
|
|
cupy-cuda114>=5.0.0b4,<11.0.0
|
|
cuda115 =
|
|
cupy-cuda115>=5.0.0b4,<11.0.0
|
|
apple =
|
|
thinc-apple-ops>=0.0.4,<1.0.0
|
|
# Language tokenizers with external dependencies
|
|
ja =
|
|
sudachipy>=0.5.2,!=0.6.1
|
|
sudachidict_core>=20211220
|
|
ko =
|
|
natto-py==0.9.0
|
|
th =
|
|
pythainlp>=2.0
|
|
|
|
[bdist_wheel]
|
|
universal = false
|
|
|
|
[sdist]
|
|
formats = gztar
|
|
|
|
[flake8]
|
|
ignore = E203, E266, E501, E731, W503, E741, F541
|
|
max-line-length = 80
|
|
select = B,C,E,F,W,T4,B9
|
|
exclude =
|
|
.env,
|
|
.git,
|
|
__pycache__,
|
|
_tokenizer_exceptions_list.py,
|
|
|
|
[tool:pytest]
|
|
markers =
|
|
slow: mark a test as slow
|
|
issue: reference specific issue
|
|
|
|
[mypy]
|
|
ignore_missing_imports = True
|
|
no_implicit_optional = True
|
|
plugins = pydantic.mypy, thinc.mypy
|
|
allow_redefinition = True
|