iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 09:21:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

v3.1: support py3.12, update formatting, replace pkg_resources with locate

Browse Source
This commit is contained in:
Elia Robyn Lake 2023-11-21 18:07:04 -05:00
parent 6fc77b4b29
commit 2be781fd1a
19 changed files with 766 additions and 419 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -11,3 +11,5 @@ wordfreq-data.tar.gz
build.dot build.dot
.pytest_cache .pytest_cache
.tox .tox
.vscode
prof

1
mypy.ini
View File

@ -1,5 +1,6 @@
[mypy] [mypy]
python_version = 3.7 python_version = 3.7
files = wordfreq
[mypy-ipadic] [mypy-ipadic]
ignore_missing_imports = True ignore_missing_imports = True

658
poetry.lock generated
View File

@ -1,3 +1,5 @@
# This file is automatically @generated by Poetry 1.4.2 and should not be changed by hand.
[[package]] [[package]]
name = "appnope" name = "appnope"
version = "0.1.3" version = "0.1.3"
@ -5,6 +7,10 @@ description = "Disable App Nap on macOS >= 10.9"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
{file = "appnope-0.1.3-py2.py3-none-any.whl", hash = "sha256:265a455292d0bd8a72453494fa24df5a11eb18373a60c7c0430889f22548605e"},
{file = "appnope-0.1.3.tar.gz", hash = "sha256:02bd91c4de869fbb1e1c50aafc4098827a7a54ab2f39d9dcba6c9547ed920e24"},
]
[[package]] [[package]]
name = "attrs" name = "attrs"
@ -13,12 +19,16 @@ description = "Classes Without Boilerplate"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.5" python-versions = ">=3.5"
files = [
{file = "attrs-22.1.0-py2.py3-none-any.whl", hash = "sha256:86efa402f67bf2df34f51a335487cf46b1ec130d02b8d39fd248abfd30da551c"},
{file = "attrs-22.1.0.tar.gz", hash = "sha256:29adc2665447e5191d0e7c568fde78b21f9672d344281d0c6e1ab085429b22b6"},
]
[package.extras] [package.extras]
dev = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "mypy (>=0.900,!=0.940)", "pytest-mypy-plugins", "zope.interface", "furo", "sphinx", "sphinx-notfound-page", "pre-commit", "cloudpickle"] dev = ["cloudpickle", "coverage[toml] (>=5.0.2)", "furo", "hypothesis", "mypy (>=0.900,!=0.940)", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "sphinx", "sphinx-notfound-page", "zope.interface"]
docs = ["furo", "sphinx", "zope.interface", "sphinx-notfound-page"] docs = ["furo", "sphinx", "sphinx-notfound-page", "zope.interface"]
tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "mypy (>=0.900,!=0.940)", "pytest-mypy-plugins", "zope.interface", "cloudpickle"] tests = ["cloudpickle", "coverage[toml] (>=5.0.2)", "hypothesis", "mypy (>=0.900,!=0.940)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "zope.interface"]
tests_no_zope = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "mypy (>=0.900,!=0.940)", "pytest-mypy-plugins", "cloudpickle"] tests-no-zope = ["cloudpickle", "coverage[toml] (>=5.0.2)", "hypothesis", "mypy (>=0.900,!=0.940)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins"]
[[package]] [[package]]
name = "backcall" name = "backcall"
@ -27,41 +37,10 @@ description = "Specifications for callback functions passed in to an API"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
[[package]] {file = "backcall-0.2.0-py2.py3-none-any.whl", hash = "sha256:fbbce6a29f263178a1f7915c1940bde0ec2b2a967566fe1c65c1dfb7422bd255"},
name = "black" {file = "backcall-0.2.0.tar.gz", hash = "sha256:5cbdbf27be5e7cfadb448baf0aa95508f91f2bbc6c6437cd9cd06e2a4c215e1e"},
version = "22.10.0" ]
description = "The uncompromising code formatter."
category = "dev"
optional = false
python-versions = ">=3.7"
[package.dependencies]
click = ">=8.0.0"
mypy-extensions = ">=0.4.3"
pathspec = ">=0.9.0"
platformdirs = ">=2"
tomli = {version = ">=1.1.0", markers = "python_full_version < \"3.11.0a7\""}
typed-ast = {version = ">=1.4.2", markers = "python_version < \"3.8\" and implementation_name == \"cpython\""}
typing-extensions = {version = ">=3.10.0.0", markers = "python_version < \"3.10\""}
[package.extras]
colorama = ["colorama (>=0.4.3)"]
d = ["aiohttp (>=3.7.4)"]
jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
uvloop = ["uvloop (>=0.15.2)"]
[[package]]
name = "click"
version = "8.1.3"
description = "Composable command line interface toolkit"
category = "dev"
optional = false
python-versions = ">=3.7"
[package.dependencies]
colorama = {version = "*", markers = "platform_system == \"Windows\""}
importlib-metadata = {version = "*", markers = "python_version < \"3.8\""}
[[package]] [[package]]
name = "colorama" name = "colorama"
@ -70,6 +49,10 @@ description = "Cross-platform colored terminal text."
category = "dev" category = "dev"
optional = false optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
files = [
{file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
]
[[package]] [[package]]
name = "decorator" name = "decorator"
@ -78,6 +61,10 @@ description = "Decorators for Humans"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.5" python-versions = ">=3.5"
files = [
{file = "decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186"},
{file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
]
[[package]] [[package]]
name = "exceptiongroup" name = "exceptiongroup"
@ -86,24 +73,14 @@ description = "Backport of PEP 654 (exception groups)"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [
{file = "exceptiongroup-1.0.0rc9-py3-none-any.whl", hash = "sha256:2e3c3fc1538a094aab74fad52d6c33fc94de3dfee3ee01f187c0e0c72aec5337"},
{file = "exceptiongroup-1.0.0rc9.tar.gz", hash = "sha256:9086a4a21ef9b31c72181c77c040a074ba0889ee56a7b289ff0afb0d97655f96"},
]
[package.extras] [package.extras]
test = ["pytest (>=6)"] test = ["pytest (>=6)"]
[[package]]
name = "flake8"
version = "4.0.1"
description = "the modular source code checker: pep8 pyflakes and co"
category = "dev"
optional = false
python-versions = ">=3.6"
[package.dependencies]
importlib-metadata = {version = "<4.3", markers = "python_version < \"3.8\""}
mccabe = ">=0.6.0,<0.7.0"
pycodestyle = ">=2.8.0,<2.9.0"
pyflakes = ">=2.4.0,<2.5.0"
[[package]] [[package]]
name = "ftfy" name = "ftfy"
version = "6.1.1" version = "6.1.1"
@ -111,25 +88,25 @@ description = "Fixes mojibake and other problems with Unicode, after the fact"
category = "main" category = "main"
optional = false optional = false
python-versions = ">=3.7,<4" python-versions = ">=3.7,<4"
files = [
{file = "ftfy-6.1.1-py3-none-any.whl", hash = "sha256:0ffd33fce16b54cccaec78d6ec73d95ad370e5df5a25255c8966a6147bd667ca"},
{file = "ftfy-6.1.1.tar.gz", hash = "sha256:bfc2019f84fcd851419152320a6375604a0f1459c281b5b199b2cd0d2e727f8f"},
]
[package.dependencies] [package.dependencies]
wcwidth = ">=0.2.5" wcwidth = ">=0.2.5"
[[package]] [[package]]
name = "importlib-metadata" name = "gprof2dot"
version = "4.2.0" version = "2022.7.29"
description = "Read metadata from Python packages" description = "Generate a dot graph from the output of several profilers."
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=2.7"
files = [
[package.dependencies] {file = "gprof2dot-2022.7.29-py2.py3-none-any.whl", hash = "sha256:f165b3851d3c52ee4915eb1bd6cca571e5759823c2cd0f71a79bda93c2dc85d6"},
typing-extensions = {version = ">=3.6.4", markers = "python_version < \"3.8\""} {file = "gprof2dot-2022.7.29.tar.gz", hash = "sha256:45b4d298bd36608fccf9511c3fd88a773f7a1abc04d6cd39445b11ba43133ec5"},
zipp = ">=0.5" ]
[package.extras]
docs = ["sphinx", "jaraco.packaging (>=8.2)", "rst.linker (>=1.9)"]
testing = ["pytest (>=4.6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.0.1)", "packaging", "pep517", "pyfakefs", "flufl.flake8", "pytest-black (>=0.3.7)", "pytest-mypy", "importlib-resources (>=1.3)"]
[[package]] [[package]]
name = "iniconfig" name = "iniconfig"
@ -138,6 +115,10 @@ description = "iniconfig: brain-dead simple config-ini parsing"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
{file = "iniconfig-1.1.1-py2.py3-none-any.whl", hash = "sha256:011e24c64b7f47f6ebd835bb12a743f2fbe9a26d4cecaa7f53bc4f35ee9da8b3"},
{file = "iniconfig-1.1.1.tar.gz", hash = "sha256:bc3af051d7d14b2ee5ef9969666def0cd1a000e121eaea580d4a313df4b37f32"},
]
[[package]] [[package]]
name = "ipadic" name = "ipadic"
@ -146,6 +127,9 @@ description = "IPAdic packaged for Python"
category = "main" category = "main"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
{file = "ipadic-1.0.0.tar.gz", hash = "sha256:f5923d31eca6131acaaf18ed28d8998665b1347b640d3a6476f64650e9a71c07"},
]
[[package]] [[package]]
name = "ipython" name = "ipython"
@ -154,6 +138,10 @@ description = "IPython: Productive Interactive Computing"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [
{file = "ipython-7.34.0-py3-none-any.whl", hash = "sha256:c175d2440a1caff76116eb719d40538fbb316e214eda85c5515c303aacbfb23e"},
{file = "ipython-7.34.0.tar.gz", hash = "sha256:af3bdb46aa292bce5615b1b2ebc76c2080c5f77f54bda2ec72461317273e7cd6"},
]
[package.dependencies] [package.dependencies]
appnope = {version = "*", markers = "sys_platform == \"darwin\""} appnope = {version = "*", markers = "sys_platform == \"darwin\""}
@ -166,6 +154,7 @@ pexpect = {version = ">4.3", markers = "sys_platform != \"win32\""}
pickleshare = "*" pickleshare = "*"
prompt-toolkit = ">=2.0.0,<3.0.0 || >3.0.0,<3.0.1 || >3.0.1,<3.1.0" prompt-toolkit = ">=2.0.0,<3.0.0 || >3.0.0,<3.0.1 || >3.0.1,<3.1.0"
pygments = "*" pygments = "*"
setuptools = ">=18.5"
traitlets = ">=4.2" traitlets = ">=4.2"
[package.extras] [package.extras]
@ -174,10 +163,10 @@ doc = ["Sphinx (>=1.3)"]
kernel = ["ipykernel"] kernel = ["ipykernel"]
nbconvert = ["nbconvert"] nbconvert = ["nbconvert"]
nbformat = ["nbformat"] nbformat = ["nbformat"]
notebook = ["notebook", "ipywidgets"] notebook = ["ipywidgets", "notebook"]
parallel = ["ipyparallel"] parallel = ["ipyparallel"]
qtconsole = ["qtconsole"] qtconsole = ["qtconsole"]
test = ["nose (>=0.10.1)", "requests", "testpath", "pygments", "nbformat", "ipykernel", "numpy (>=1.17)"] test = ["ipykernel", "nbformat", "nose (>=0.10.1)", "numpy (>=1.17)", "pygments", "requests", "testpath"]
[[package]] [[package]]
name = "jedi" name = "jedi"
@ -186,6 +175,10 @@ description = "An autocompletion tool for Python that can be used for text edito
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [
{file = "jedi-0.18.1-py2.py3-none-any.whl", hash = "sha256:637c9635fcf47945ceb91cd7f320234a7be540ded6f3e99a50cb6febdfd1ba8d"},
{file = "jedi-0.18.1.tar.gz", hash = "sha256:74137626a64a99c8eb6ae5832d99b3bdd7d29a3850fe2aa80a4126b2a7d949ab"},
]
[package.dependencies] [package.dependencies]
parso = ">=0.8.0,<0.9.0" parso = ">=0.8.0,<0.9.0"
@ -201,6 +194,9 @@ description = "Chinese Words Segmentation Utilities"
category = "main" category = "main"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
{file = "jieba-0.42.1.tar.gz", hash = "sha256:055ca12f62674fafed09427f176506079bc135638a14e23e25be909131928db2"},
]
[[package]] [[package]]
name = "langcodes" name = "langcodes"
@ -209,10 +205,26 @@ description = "Tools for labeling human languages with IETF language tags"
category = "main" category = "main"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [
{file = "langcodes-3.3.0-py3-none-any.whl", hash = "sha256:4d89fc9acb6e9c8fdef70bcdf376113a3db09b67285d9e1d534de6d8818e7e69"},
{file = "langcodes-3.3.0.tar.gz", hash = "sha256:794d07d5a28781231ac335a1561b8442f8648ca07cd518310aeb45d6f0807ef6"},
]
[package.extras] [package.extras]
data = ["language-data (>=1.1,<2.0)"] data = ["language-data (>=1.1,<2.0)"]
[[package]]
name = "locate"
version = "1.1.1"
description = "Locate the file location of your current running script."
category = "main"
optional = false
python-versions = ">=3.4"
files = [
{file = "locate-1.1.1-py3-none-any.whl", hash = "sha256:9e5e2f3516639240f4d975c08e95ae6a24ff4dd63d228f927541cdec30105755"},
{file = "locate-1.1.1.tar.gz", hash = "sha256:432750f5b7e89f8c99942ca7d8722ccd1e7954b20e6a973027fccb6cc00af857"},
]
[[package]] [[package]]
name = "matplotlib-inline" name = "matplotlib-inline"
version = "0.1.6" version = "0.1.6"
@ -220,18 +232,14 @@ description = "Inline Matplotlib backend for Jupyter"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.5" python-versions = ">=3.5"
files = [
{file = "matplotlib-inline-0.1.6.tar.gz", hash = "sha256:f887e5f10ba98e8d2b150ddcf4702c1e5f8b3a20005eb0f74bfdbd360ee6f304"},
{file = "matplotlib_inline-0.1.6-py3-none-any.whl", hash = "sha256:f1f41aab5328aa5aaea9b16d083b128102f8712542f819fe7e6a420ff581b311"},
]
[package.dependencies] [package.dependencies]
traitlets = "*" traitlets = "*"
[[package]]
name = "mccabe"
version = "0.6.1"
description = "McCabe checker, plugin for flake8"
category = "dev"
optional = false
python-versions = "*"
[[package]] [[package]]
name = "mecab-ko-dic" name = "mecab-ko-dic"
version = "1.0.0" version = "1.0.0"
@ -239,6 +247,9 @@ description = "mecab-ko-dic packaged for Python"
category = "main" category = "main"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
{file = "mecab-ko-dic-1.0.0.tar.gz", hash = "sha256:3ba22858736e02e8a0e92f2a7f099528c733ae47701b29d12c75e982a85d1f11"},
]
[[package]] [[package]]
name = "mecab-python3" name = "mecab-python3"
@ -247,6 +258,29 @@ description = "Python wrapper for the MeCab morphological analyzer for Japanese"
category = "main" category = "main"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
{file = "mecab-python3-1.0.5.tar.gz", hash = "sha256:e703d78c88a671abb8170351644850015d9bbfab31530a3b40d12481a6779a11"},
{file = "mecab_python3-1.0.5-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:8a64bd228704ed9b24da5cbd6c4e325ef22310227153ef481f9037183351aa10"},
{file = "mecab_python3-1.0.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bf083884116fa05ca0394c4c8d62013a4954fbac414c33a1931906ddf0f3585a"},
{file = "mecab_python3-1.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1fe020df27b249f43df3d38b84473d226e36d6d4a31f951cedbddabfcc450e36"},
{file = "mecab_python3-1.0.5-cp310-cp310-win_amd64.whl", hash = "sha256:644f781de083311fcf81f7d55f21a756ceef7ebae7c111bd50a2c9d0855c1927"},
{file = "mecab_python3-1.0.5-cp36-cp36m-macosx_10_14_x86_64.whl", hash = "sha256:4309a91f0d5b66d3f0e8c9ba5a4d3cf7dbac1334269338704599820e051d1d7f"},
{file = "mecab_python3-1.0.5-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7be2d1cd2ecd1f04b91eb0e26c906f21b50b8526e977f7f01f3901f9a6306944"},
{file = "mecab_python3-1.0.5-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:644bbde31ab1244ff18fb1dcac1e5fee8121f8b27a5c3e041c01ebc301df9266"},
{file = "mecab_python3-1.0.5-cp36-cp36m-win_amd64.whl", hash = "sha256:401a2d1608b6503cb755d7d864ad74b64a7a4346309235f84577de807bb29050"},
{file = "mecab_python3-1.0.5-cp37-cp37m-macosx_10_14_x86_64.whl", hash = "sha256:5f91d5d8a9ac0ea7351e5e2423df98dd463b02013e006b18096cd365de37b2a9"},
{file = "mecab_python3-1.0.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bc8ce0151b973f4ca15e651619264442011568ebe48c6fce51d55e64f7e5c2e1"},
{file = "mecab_python3-1.0.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3e381df4c55f3ec5bccbb5625c65c54ecf982c215574d1102aff2803ac1a24cd"},
{file = "mecab_python3-1.0.5-cp37-cp37m-win_amd64.whl", hash = "sha256:8eaaa78227f470c4cf1d6c2a87b92889041f317517fbe65e635b86ea0c84a194"},
{file = "mecab_python3-1.0.5-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:dd8601565dd1331ee5cd67bcc45f713cebc14b730ee2e956ed120a0ec6e4fd8a"},
{file = "mecab_python3-1.0.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:76a40f717f9592bd12edc7bcf1fa869f4c8058e5d0b80d4cc6c301435afb1f96"},
{file = "mecab_python3-1.0.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9f299d6ef96495371f5a622a7004a205e303dabba1fc3a7f9a07e741e315ed2b"},
{file = "mecab_python3-1.0.5-cp38-cp38-win_amd64.whl", hash = "sha256:4cdb07edbbd508d9b98ac9529e0ff0b89d93e50a6beeb7b8b946439594bf5e01"},
{file = "mecab_python3-1.0.5-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:eb412a25e485e33d7ab69262b58f7365b727f8c447e4c9c1c56b5fd91414ecd2"},
{file = "mecab_python3-1.0.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:91e8ac11ef4440418312dd4f1f200f7957fdc0148bb49dc049264c5d07bed527"},
{file = "mecab_python3-1.0.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ae1c126cf4982035794042280998066c8b6d26eb89136731078d9105a7070c13"},
{file = "mecab_python3-1.0.5-cp39-cp39-win_amd64.whl", hash = "sha256:34a196c6a410e57f975ee077d075ac994b94bb6930b04e207e59e7c7521ecb58"},
]
[package.extras] [package.extras]
unidic = ["unidic"] unidic = ["unidic"]
@ -254,37 +288,129 @@ unidic-lite = ["unidic-lite"]
[[package]] [[package]]
name = "msgpack" name = "msgpack"
version = "1.0.4" version = "1.0.7"
description = "MessagePack serializer" description = "MessagePack serializer"
category = "main" category = "main"
optional = false optional = false
python-versions = "*" python-versions = ">=3.8"
files = [
{file = "msgpack-1.0.7-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:04ad6069c86e531682f9e1e71b71c1c3937d6014a7c3e9edd2aa81ad58842862"},
{file = "msgpack-1.0.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cca1b62fe70d761a282496b96a5e51c44c213e410a964bdffe0928e611368329"},
{file = "msgpack-1.0.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e50ebce52f41370707f1e21a59514e3375e3edd6e1832f5e5235237db933c98b"},
{file = "msgpack-1.0.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4a7b4f35de6a304b5533c238bee86b670b75b03d31b7797929caa7a624b5dda6"},
{file = "msgpack-1.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28efb066cde83c479dfe5a48141a53bc7e5f13f785b92ddde336c716663039ee"},
{file = "msgpack-1.0.7-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4cb14ce54d9b857be9591ac364cb08dc2d6a5c4318c1182cb1d02274029d590d"},
{file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b573a43ef7c368ba4ea06050a957c2a7550f729c31f11dd616d2ac4aba99888d"},
{file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ccf9a39706b604d884d2cb1e27fe973bc55f2890c52f38df742bc1d79ab9f5e1"},
{file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:cb70766519500281815dfd7a87d3a178acf7ce95390544b8c90587d76b227681"},
{file = "msgpack-1.0.7-cp310-cp310-win32.whl", hash = "sha256:b610ff0f24e9f11c9ae653c67ff8cc03c075131401b3e5ef4b82570d1728f8a9"},
{file = "msgpack-1.0.7-cp310-cp310-win_amd64.whl", hash = "sha256:a40821a89dc373d6427e2b44b572efc36a2778d3f543299e2f24eb1a5de65415"},
{file = "msgpack-1.0.7-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:576eb384292b139821c41995523654ad82d1916da6a60cff129c715a6223ea84"},
{file = "msgpack-1.0.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:730076207cb816138cf1af7f7237b208340a2c5e749707457d70705715c93b93"},
{file = "msgpack-1.0.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:85765fdf4b27eb5086f05ac0491090fc76f4f2b28e09d9350c31aac25a5aaff8"},
{file = "msgpack-1.0.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3476fae43db72bd11f29a5147ae2f3cb22e2f1a91d575ef130d2bf49afd21c46"},
{file = "msgpack-1.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d4c80667de2e36970ebf74f42d1088cc9ee7ef5f4e8c35eee1b40eafd33ca5b"},
{file = "msgpack-1.0.7-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5b0bf0effb196ed76b7ad883848143427a73c355ae8e569fa538365064188b8e"},
{file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:f9a7c509542db4eceed3dcf21ee5267ab565a83555c9b88a8109dcecc4709002"},
{file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:84b0daf226913133f899ea9b30618722d45feffa67e4fe867b0b5ae83a34060c"},
{file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:ec79ff6159dffcc30853b2ad612ed572af86c92b5168aa3fc01a67b0fa40665e"},
{file = "msgpack-1.0.7-cp311-cp311-win32.whl", hash = "sha256:3e7bf4442b310ff154b7bb9d81eb2c016b7d597e364f97d72b1acc3817a0fdc1"},
{file = "msgpack-1.0.7-cp311-cp311-win_amd64.whl", hash = "sha256:3f0c8c6dfa6605ab8ff0611995ee30d4f9fcff89966cf562733b4008a3d60d82"},
{file = "msgpack-1.0.7-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f0936e08e0003f66bfd97e74ee530427707297b0d0361247e9b4f59ab78ddc8b"},
{file = "msgpack-1.0.7-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:98bbd754a422a0b123c66a4c341de0474cad4a5c10c164ceed6ea090f3563db4"},
{file = "msgpack-1.0.7-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b291f0ee7961a597cbbcc77709374087fa2a9afe7bdb6a40dbbd9b127e79afee"},
{file = "msgpack-1.0.7-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ebbbba226f0a108a7366bf4b59bf0f30a12fd5e75100c630267d94d7f0ad20e5"},
{file = "msgpack-1.0.7-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e2d69948e4132813b8d1131f29f9101bc2c915f26089a6d632001a5c1349672"},
{file = "msgpack-1.0.7-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bdf38ba2d393c7911ae989c3bbba510ebbcdf4ecbdbfec36272abe350c454075"},
{file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:993584fc821c58d5993521bfdcd31a4adf025c7d745bbd4d12ccfecf695af5ba"},
{file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:52700dc63a4676669b341ba33520f4d6e43d3ca58d422e22ba66d1736b0a6e4c"},
{file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e45ae4927759289c30ccba8d9fdce62bb414977ba158286b5ddaf8df2cddb5c5"},
{file = "msgpack-1.0.7-cp312-cp312-win32.whl", hash = "sha256:27dcd6f46a21c18fa5e5deed92a43d4554e3df8d8ca5a47bf0615d6a5f39dbc9"},
{file = "msgpack-1.0.7-cp312-cp312-win_amd64.whl", hash = "sha256:7687e22a31e976a0e7fc99c2f4d11ca45eff652a81eb8c8085e9609298916dcf"},
{file = "msgpack-1.0.7-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5b6ccc0c85916998d788b295765ea0e9cb9aac7e4a8ed71d12e7d8ac31c23c95"},
{file = "msgpack-1.0.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:235a31ec7db685f5c82233bddf9858748b89b8119bf4538d514536c485c15fe0"},
{file = "msgpack-1.0.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cab3db8bab4b7e635c1c97270d7a4b2a90c070b33cbc00c99ef3f9be03d3e1f7"},
{file = "msgpack-1.0.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0bfdd914e55e0d2c9e1526de210f6fe8ffe9705f2b1dfcc4aecc92a4cb4b533d"},
{file = "msgpack-1.0.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36e17c4592231a7dbd2ed09027823ab295d2791b3b1efb2aee874b10548b7524"},
{file = "msgpack-1.0.7-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:38949d30b11ae5f95c3c91917ee7a6b239f5ec276f271f28638dec9156f82cfc"},
{file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:ff1d0899f104f3921d94579a5638847f783c9b04f2d5f229392ca77fba5b82fc"},
{file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:dc43f1ec66eb8440567186ae2f8c447d91e0372d793dfe8c222aec857b81a8cf"},
{file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:dd632777ff3beaaf629f1ab4396caf7ba0bdd075d948a69460d13d44357aca4c"},
{file = "msgpack-1.0.7-cp38-cp38-win32.whl", hash = "sha256:4e71bc4416de195d6e9b4ee93ad3f2f6b2ce11d042b4d7a7ee00bbe0358bd0c2"},
{file = "msgpack-1.0.7-cp38-cp38-win_amd64.whl", hash = "sha256:8f5b234f567cf76ee489502ceb7165c2a5cecec081db2b37e35332b537f8157c"},
{file = "msgpack-1.0.7-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:bfef2bb6ef068827bbd021017a107194956918ab43ce4d6dc945ffa13efbc25f"},
{file = "msgpack-1.0.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:484ae3240666ad34cfa31eea7b8c6cd2f1fdaae21d73ce2974211df099a95d81"},
{file = "msgpack-1.0.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3967e4ad1aa9da62fd53e346ed17d7b2e922cba5ab93bdd46febcac39be636fc"},
{file = "msgpack-1.0.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8dd178c4c80706546702c59529ffc005681bd6dc2ea234c450661b205445a34d"},
{file = "msgpack-1.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f6ffbc252eb0d229aeb2f9ad051200668fc3a9aaa8994e49f0cb2ffe2b7867e7"},
{file = "msgpack-1.0.7-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:822ea70dc4018c7e6223f13affd1c5c30c0f5c12ac1f96cd8e9949acddb48a61"},
{file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:384d779f0d6f1b110eae74cb0659d9aa6ff35aaf547b3955abf2ab4c901c4819"},
{file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:f64e376cd20d3f030190e8c32e1c64582eba56ac6dc7d5b0b49a9d44021b52fd"},
{file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5ed82f5a7af3697b1c4786053736f24a0efd0a1b8a130d4c7bfee4b9ded0f08f"},
{file = "msgpack-1.0.7-cp39-cp39-win32.whl", hash = "sha256:f26a07a6e877c76a88e3cecac8531908d980d3d5067ff69213653649ec0f60ad"},
{file = "msgpack-1.0.7-cp39-cp39-win_amd64.whl", hash = "sha256:1dc93e8e4653bdb5910aed79f11e165c85732067614f180f70534f056da97db3"},
{file = "msgpack-1.0.7.tar.gz", hash = "sha256:572efc93db7a4d27e404501975ca6d2d9775705c2d922390d878fcf768d92c87"},
]
[[package]] [[package]]
name = "mypy" name = "mypy"
version = "0.931" version = "1.7.0"
description = "Optional static typing for Python" description = "Optional static typing for Python"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.8"
files = [
{file = "mypy-1.7.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:5da84d7bf257fd8f66b4f759a904fd2c5a765f70d8b52dde62b521972a0a2357"},
{file = "mypy-1.7.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a3637c03f4025f6405737570d6cbfa4f1400eb3c649317634d273687a09ffc2f"},
{file = "mypy-1.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b633f188fc5ae1b6edca39dae566974d7ef4e9aaaae00bc36efe1f855e5173ac"},
{file = "mypy-1.7.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:d6ed9a3997b90c6f891138e3f83fb8f475c74db4ccaa942a1c7bf99e83a989a1"},
{file = "mypy-1.7.0-cp310-cp310-win_amd64.whl", hash = "sha256:1fe46e96ae319df21359c8db77e1aecac8e5949da4773c0274c0ef3d8d1268a9"},
{file = "mypy-1.7.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:df67fbeb666ee8828f675fee724cc2cbd2e4828cc3df56703e02fe6a421b7401"},
{file = "mypy-1.7.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a79cdc12a02eb526d808a32a934c6fe6df07b05f3573d210e41808020aed8b5d"},
{file = "mypy-1.7.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f65f385a6f43211effe8c682e8ec3f55d79391f70a201575def73d08db68ead1"},
{file = "mypy-1.7.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0e81ffd120ee24959b449b647c4b2fbfcf8acf3465e082b8d58fd6c4c2b27e46"},
{file = "mypy-1.7.0-cp311-cp311-win_amd64.whl", hash = "sha256:f29386804c3577c83d76520abf18cfcd7d68264c7e431c5907d250ab502658ee"},
{file = "mypy-1.7.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:87c076c174e2c7ef8ab416c4e252d94c08cd4980a10967754f91571070bf5fbe"},
{file = "mypy-1.7.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6cb8d5f6d0fcd9e708bb190b224089e45902cacef6f6915481806b0c77f7786d"},
{file = "mypy-1.7.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d93e76c2256aa50d9c82a88e2f569232e9862c9982095f6d54e13509f01222fc"},
{file = "mypy-1.7.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:cddee95dea7990e2215576fae95f6b78a8c12f4c089d7e4367564704e99118d3"},
{file = "mypy-1.7.0-cp312-cp312-win_amd64.whl", hash = "sha256:d01921dbd691c4061a3e2ecdbfbfad029410c5c2b1ee88946bf45c62c6c91210"},
{file = "mypy-1.7.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:185cff9b9a7fec1f9f7d8352dff8a4c713b2e3eea9c6c4b5ff7f0edf46b91e41"},
{file = "mypy-1.7.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:7a7b1e399c47b18feb6f8ad4a3eef3813e28c1e871ea7d4ea5d444b2ac03c418"},
{file = "mypy-1.7.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc9fe455ad58a20ec68599139ed1113b21f977b536a91b42bef3ffed5cce7391"},
{file = "mypy-1.7.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:d0fa29919d2e720c8dbaf07d5578f93d7b313c3e9954c8ec05b6d83da592e5d9"},
{file = "mypy-1.7.0-cp38-cp38-win_amd64.whl", hash = "sha256:2b53655a295c1ed1af9e96b462a736bf083adba7b314ae775563e3fb4e6795f5"},
{file = "mypy-1.7.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c1b06b4b109e342f7dccc9efda965fc3970a604db70f8560ddfdee7ef19afb05"},
{file = "mypy-1.7.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:bf7a2f0a6907f231d5e41adba1a82d7d88cf1f61a70335889412dec99feeb0f8"},
{file = "mypy-1.7.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:551d4a0cdcbd1d2cccdcc7cb516bb4ae888794929f5b040bb51aae1846062901"},
{file = "mypy-1.7.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:55d28d7963bef00c330cb6461db80b0b72afe2f3c4e2963c99517cf06454e665"},
{file = "mypy-1.7.0-cp39-cp39-win_amd64.whl", hash = "sha256:870bd1ffc8a5862e593185a4c169804f2744112b4a7c55b93eb50f48e7a77010"},
{file = "mypy-1.7.0-py3-none-any.whl", hash = "sha256:96650d9a4c651bc2a4991cf46f100973f656d69edc7faf91844e87fe627f7e96"},
{file = "mypy-1.7.0.tar.gz", hash = "sha256:1e280b5697202efa698372d2f39e9a6713a0395a756b1c6bd48995f8d72690dc"},
]
[package.dependencies] [package.dependencies]
mypy-extensions = ">=0.4.3" mypy-extensions = ">=1.0.0"
tomli = ">=1.1.0" tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
typed-ast = {version = ">=1.4.0,<2", markers = "python_version < \"3.8\""} typing-extensions = ">=4.1.0"
typing-extensions = ">=3.10"
[package.extras] [package.extras]
dmypy = ["psutil (>=4.0)"] dmypy = ["psutil (>=4.0)"]
python2 = ["typed-ast (>=1.4.0,<2)"] install-types = ["pip"]
mypyc = ["setuptools (>=50)"]
reports = ["lxml"]
[[package]] [[package]]
name = "mypy-extensions" name = "mypy-extensions"
version = "0.4.3" version = "1.0.0"
description = "Experimental type system extensions for programs checked with the mypy typechecker." description = "Type system extensions for programs checked with the mypy type checker."
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = ">=3.5"
files = [
{file = "mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d"},
{file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"},
]
[[package]] [[package]]
name = "packaging" name = "packaging"
@ -293,6 +419,10 @@ description = "Core utilities for Python packages"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [
{file = "packaging-21.3-py3-none-any.whl", hash = "sha256:ef103e05f519cdc783ae24ea4e2e0f508a9c99b2d4969652eed6a2e1ea5bd522"},
{file = "packaging-21.3.tar.gz", hash = "sha256:dd47c42927d89ab911e606518907cc2d3a1f38bbd026385970643f9c5b8ecfeb"},
]
[package.dependencies] [package.dependencies]
pyparsing = ">=2.0.2,<3.0.5 || >3.0.5" pyparsing = ">=2.0.2,<3.0.5 || >3.0.5"
@ -304,19 +434,15 @@ description = "A Python Parser"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [
{file = "parso-0.8.3-py2.py3-none-any.whl", hash = "sha256:c001d4636cd3aecdaf33cbb40aebb59b094be2a74c556778ef5576c175e19e75"},
{file = "parso-0.8.3.tar.gz", hash = "sha256:8c07be290bb59f03588915921e29e8a50002acaf2cdc5fa0e0114f91709fafa0"},
]
[package.extras] [package.extras]
qa = ["flake8 (==3.8.3)", "mypy (==0.782)"] qa = ["flake8 (==3.8.3)", "mypy (==0.782)"]
testing = ["docopt", "pytest (<6.0.0)"] testing = ["docopt", "pytest (<6.0.0)"]
[[package]]
name = "pathspec"
version = "0.10.1"
description = "Utility library for gitignore style pattern matching of file paths."
category = "dev"
optional = false
python-versions = ">=3.7"
[[package]] [[package]]
name = "pexpect" name = "pexpect"
version = "4.8.0" version = "4.8.0"
@ -324,6 +450,10 @@ description = "Pexpect allows easy control of interactive console applications."
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
{file = "pexpect-4.8.0-py2.py3-none-any.whl", hash = "sha256:0b48a55dcb3c05f3329815901ea4fc1537514d6ba867a152b581d69ae3710937"},
{file = "pexpect-4.8.0.tar.gz", hash = "sha256:fc65a43959d153d0114afe13997d439c22823a27cefceb5ff35c2178c6784c0c"},
]
[package.dependencies] [package.dependencies]
ptyprocess = ">=0.5" ptyprocess = ">=0.5"
@ -335,18 +465,10 @@ description = "Tiny 'shelve'-like database with concurrency support"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
[[package]] {file = "pickleshare-0.7.5-py2.py3-none-any.whl", hash = "sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56"},
name = "platformdirs" {file = "pickleshare-0.7.5.tar.gz", hash = "sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca"},
version = "2.5.2" ]
description = "A small Python module for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
category = "dev"
optional = false
python-versions = ">=3.7"
[package.extras]
docs = ["furo (>=2021.7.5b38)", "proselint (>=0.10.2)", "sphinx-autodoc-typehints (>=1.12)", "sphinx (>=4)"]
test = ["appdirs (==1.4.4)", "pytest-cov (>=2.7)", "pytest-mock (>=3.6)", "pytest (>=6)"]
[[package]] [[package]]
name = "pluggy" name = "pluggy"
@ -355,13 +477,14 @@ description = "plugin and hook calling mechanisms for python"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [
[package.dependencies] {file = "pluggy-1.0.0-py2.py3-none-any.whl", hash = "sha256:74134bbf457f031a36d68416e1509f34bd5ccc019f0bcc952c7b909d06b37bd3"},
importlib-metadata = {version = ">=0.12", markers = "python_version < \"3.8\""} {file = "pluggy-1.0.0.tar.gz", hash = "sha256:4224373bacce55f955a878bf9cfa763c1e360858e330072059e10bad68531159"},
]
[package.extras] [package.extras]
testing = ["pytest-benchmark", "pytest"] dev = ["pre-commit", "tox"]
dev = ["tox", "pre-commit"] testing = ["pytest", "pytest-benchmark"]
[[package]] [[package]]
name = "prompt-toolkit" name = "prompt-toolkit"
@ -370,6 +493,10 @@ description = "Library for building powerful interactive command lines in Python
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6.2" python-versions = ">=3.6.2"
files = [
{file = "prompt_toolkit-3.0.31-py3-none-any.whl", hash = "sha256:9696f386133df0fc8ca5af4895afe5d78f5fcfe5258111c2a79a1c3e41ffa96d"},
{file = "prompt_toolkit-3.0.31.tar.gz", hash = "sha256:9ada952c9d1787f52ff6d5f3484d0b4df8952787c087edf6a1f7c2cb1ea88148"},
]
[package.dependencies] [package.dependencies]
wcwidth = "*" wcwidth = "*"
@ -381,22 +508,10 @@ description = "Run a subprocess in a pseudo terminal"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
[[package]] {file = "ptyprocess-0.7.0-py2.py3-none-any.whl", hash = "sha256:4b41f3967fce3af57cc7e94b888626c18bf37a083e3651ca8feeb66d492fef35"},
name = "pycodestyle" {file = "ptyprocess-0.7.0.tar.gz", hash = "sha256:5c5d0a3b48ceee0b48485e0c26037c0acd7d29765ca3fbb5cb3831d347423220"},
version = "2.8.0" ]
description = "Python style guide checker"
category = "dev"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
[[package]]
name = "pyflakes"
version = "2.4.0"
description = "passive checker of Python programs"
category = "dev"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
[[package]] [[package]]
name = "pygments" name = "pygments"
@ -405,6 +520,10 @@ description = "Pygments is a syntax highlighting package written in Python."
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [
{file = "Pygments-2.13.0-py3-none-any.whl", hash = "sha256:f643f331ab57ba3c9d89212ee4a2dabc6e94f117cf4eefde99a0574720d14c42"},
{file = "Pygments-2.13.0.tar.gz", hash = "sha256:56a8508ae95f98e2b9bdf93a6be5ae3f7d8af858b43e02c5a2ff083726be40c1"},
]
[package.extras] [package.extras]
plugins = ["importlib-metadata"] plugins = ["importlib-metadata"]
@ -416,9 +535,13 @@ description = "pyparsing module - Classes and methods to define and execute pars
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6.8" python-versions = ">=3.6.8"
files = [
{file = "pyparsing-3.0.9-py3-none-any.whl", hash = "sha256:5026bae9a10eeaefb61dab2f09052b9f4307d44aee4eda64b309723d8d206bbc"},
{file = "pyparsing-3.0.9.tar.gz", hash = "sha256:2b020ecf7d21b687f219b71ecad3631f644a47f01403fa1d1036b0c6416d70fb"},
]
[package.extras] [package.extras]
diagrams = ["railroad-diagrams", "jinja2"] diagrams = ["jinja2", "railroad-diagrams"]
[[package]] [[package]]
name = "pytest" name = "pytest"
@ -427,12 +550,15 @@ description = "pytest: simple powerful testing with Python"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [
{file = "pytest-7.2.0-py3-none-any.whl", hash = "sha256:892f933d339f068883b6fd5a459f03d85bfcb355e4981e146d2c7616c21fef71"},
{file = "pytest-7.2.0.tar.gz", hash = "sha256:c4014eb40e10f11f355ad4e3c2fb2c6c6d1919c73f3b5a433de4708202cade59"},
]
[package.dependencies] [package.dependencies]
attrs = ">=19.2.0" attrs = ">=19.2.0"
colorama = {version = "*", markers = "sys_platform == \"win32\""} colorama = {version = "*", markers = "sys_platform == \"win32\""}
exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""} exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
importlib-metadata = {version = ">=0.12", markers = "python_version < \"3.8\""}
iniconfig = "*" iniconfig = "*"
packaging = "*" packaging = "*"
pluggy = ">=0.12,<2.0" pluggy = ">=0.12,<2.0"
@ -441,13 +567,179 @@ tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
[package.extras] [package.extras]
testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "xmlschema"] testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "xmlschema"]
[[package]]
name = "pytest-profiling"
version = "1.7.0"
description = "Profiling plugin for py.test"
category = "dev"
optional = false
python-versions = "*"
files = [
{file = "pytest-profiling-1.7.0.tar.gz", hash = "sha256:93938f147662225d2b8bd5af89587b979652426a8a6ffd7e73ec4a23e24b7f29"},
{file = "pytest_profiling-1.7.0-py2.py3-none-any.whl", hash = "sha256:999cc9ac94f2e528e3f5d43465da277429984a1c237ae9818f8cfd0b06acb019"},
]
[package.dependencies]
gprof2dot = "*"
pytest = "*"
six = "*"
[package.extras]
tests = ["pytest-virtualenv"]
[[package]] [[package]]
name = "regex" name = "regex"
version = "2022.9.13" version = "2023.10.3"
description = "Alternative regular expression module, to replace re." description = "Alternative regular expression module, to replace re."
category = "main" category = "main"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.7"
files = [
{file = "regex-2023.10.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:4c34d4f73ea738223a094d8e0ffd6d2c1a1b4c175da34d6b0de3d8d69bee6bcc"},
{file = "regex-2023.10.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a8f4e49fc3ce020f65411432183e6775f24e02dff617281094ba6ab079ef0915"},
{file = "regex-2023.10.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4cd1bccf99d3ef1ab6ba835308ad85be040e6a11b0977ef7ea8c8005f01a3c29"},
{file = "regex-2023.10.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:81dce2ddc9f6e8f543d94b05d56e70d03a0774d32f6cca53e978dc01e4fc75b8"},
{file = "regex-2023.10.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9c6b4d23c04831e3ab61717a707a5d763b300213db49ca680edf8bf13ab5d91b"},
{file = "regex-2023.10.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c15ad0aee158a15e17e0495e1e18741573d04eb6da06d8b84af726cfc1ed02ee"},
{file = "regex-2023.10.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6239d4e2e0b52c8bd38c51b760cd870069f0bdf99700a62cd509d7a031749a55"},
{file = "regex-2023.10.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:4a8bf76e3182797c6b1afa5b822d1d5802ff30284abe4599e1247be4fd6b03be"},
{file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d9c727bbcf0065cbb20f39d2b4f932f8fa1631c3e01fcedc979bd4f51fe051c5"},
{file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:3ccf2716add72f80714b9a63899b67fa711b654be3fcdd34fa391d2d274ce767"},
{file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:107ac60d1bfdc3edb53be75e2a52aff7481b92817cfdddd9b4519ccf0e54a6ff"},
{file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:00ba3c9818e33f1fa974693fb55d24cdc8ebafcb2e4207680669d8f8d7cca79a"},
{file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f0a47efb1dbef13af9c9a54a94a0b814902e547b7f21acb29434504d18f36e3a"},
{file = "regex-2023.10.3-cp310-cp310-win32.whl", hash = "sha256:36362386b813fa6c9146da6149a001b7bd063dabc4d49522a1f7aa65b725c7ec"},
{file = "regex-2023.10.3-cp310-cp310-win_amd64.whl", hash = "sha256:c65a3b5330b54103e7d21cac3f6bf3900d46f6d50138d73343d9e5b2900b2353"},
{file = "regex-2023.10.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:90a79bce019c442604662d17bf69df99090e24cdc6ad95b18b6725c2988a490e"},
{file = "regex-2023.10.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c7964c2183c3e6cce3f497e3a9f49d182e969f2dc3aeeadfa18945ff7bdd7051"},
{file = "regex-2023.10.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ef80829117a8061f974b2fda8ec799717242353bff55f8a29411794d635d964"},
{file = "regex-2023.10.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5addc9d0209a9afca5fc070f93b726bf7003bd63a427f65ef797a931782e7edc"},
{file = "regex-2023.10.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c148bec483cc4b421562b4bcedb8e28a3b84fcc8f0aa4418e10898f3c2c0eb9b"},
{file = "regex-2023.10.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d1f21af4c1539051049796a0f50aa342f9a27cde57318f2fc41ed50b0dbc4ac"},
{file = "regex-2023.10.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0b9ac09853b2a3e0d0082104036579809679e7715671cfbf89d83c1cb2a30f58"},
{file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ebedc192abbc7fd13c5ee800e83a6df252bec691eb2c4bedc9f8b2e2903f5e2a"},
{file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:d8a993c0a0ffd5f2d3bda23d0cd75e7086736f8f8268de8a82fbc4bd0ac6791e"},
{file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:be6b7b8d42d3090b6c80793524fa66c57ad7ee3fe9722b258aec6d0672543fd0"},
{file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4023e2efc35a30e66e938de5aef42b520c20e7eda7bb5fb12c35e5d09a4c43f6"},
{file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0d47840dc05e0ba04fe2e26f15126de7c755496d5a8aae4a08bda4dd8d646c54"},
{file = "regex-2023.10.3-cp311-cp311-win32.whl", hash = "sha256:9145f092b5d1977ec8c0ab46e7b3381b2fd069957b9862a43bd383e5c01d18c2"},
{file = "regex-2023.10.3-cp311-cp311-win_amd64.whl", hash = "sha256:b6104f9a46bd8743e4f738afef69b153c4b8b592d35ae46db07fc28ae3d5fb7c"},
{file = "regex-2023.10.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:bff507ae210371d4b1fe316d03433ac099f184d570a1a611e541923f78f05037"},
{file = "regex-2023.10.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:be5e22bbb67924dea15039c3282fa4cc6cdfbe0cbbd1c0515f9223186fc2ec5f"},
{file = "regex-2023.10.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4a992f702c9be9c72fa46f01ca6e18d131906a7180950958f766c2aa294d4b41"},
{file = "regex-2023.10.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7434a61b158be563c1362d9071358f8ab91b8d928728cd2882af060481244c9e"},
{file = "regex-2023.10.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c2169b2dcabf4e608416f7f9468737583ce5f0a6e8677c4efbf795ce81109d7c"},
{file = "regex-2023.10.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9e908ef5889cda4de038892b9accc36d33d72fb3e12c747e2799a0e806ec841"},
{file = "regex-2023.10.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:12bd4bc2c632742c7ce20db48e0d99afdc05e03f0b4c1af90542e05b809a03d9"},
{file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:bc72c231f5449d86d6c7d9cc7cd819b6eb30134bb770b8cfdc0765e48ef9c420"},
{file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bce8814b076f0ce5766dc87d5a056b0e9437b8e0cd351b9a6c4e1134a7dfbda9"},
{file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:ba7cd6dc4d585ea544c1412019921570ebd8a597fabf475acc4528210d7c4a6f"},
{file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:b0c7d2f698e83f15228ba41c135501cfe7d5740181d5903e250e47f617eb4292"},
{file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:5a8f91c64f390ecee09ff793319f30a0f32492e99f5dc1c72bc361f23ccd0a9a"},
{file = "regex-2023.10.3-cp312-cp312-win32.whl", hash = "sha256:ad08a69728ff3c79866d729b095872afe1e0557251da4abb2c5faff15a91d19a"},
{file = "regex-2023.10.3-cp312-cp312-win_amd64.whl", hash = "sha256:39cdf8d141d6d44e8d5a12a8569d5a227f645c87df4f92179bd06e2e2705e76b"},
{file = "regex-2023.10.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:4a3ee019a9befe84fa3e917a2dd378807e423d013377a884c1970a3c2792d293"},
{file = "regex-2023.10.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:76066d7ff61ba6bf3cb5efe2428fc82aac91802844c022d849a1f0f53820502d"},
{file = "regex-2023.10.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bfe50b61bab1b1ec260fa7cd91106fa9fece57e6beba05630afe27c71259c59b"},
{file = "regex-2023.10.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9fd88f373cb71e6b59b7fa597e47e518282455c2734fd4306a05ca219a1991b0"},
{file = "regex-2023.10.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3ab05a182c7937fb374f7e946f04fb23a0c0699c0450e9fb02ef567412d2fa3"},
{file = "regex-2023.10.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dac37cf08fcf2094159922edc7a2784cfcc5c70f8354469f79ed085f0328ebdf"},
{file = "regex-2023.10.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:e54ddd0bb8fb626aa1f9ba7b36629564544954fff9669b15da3610c22b9a0991"},
{file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:3367007ad1951fde612bf65b0dffc8fd681a4ab98ac86957d16491400d661302"},
{file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:16f8740eb6dbacc7113e3097b0a36065a02e37b47c936b551805d40340fb9971"},
{file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:f4f2ca6df64cbdd27f27b34f35adb640b5d2d77264228554e68deda54456eb11"},
{file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:39807cbcbe406efca2a233884e169d056c35aa7e9f343d4e78665246a332f597"},
{file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:7eece6fbd3eae4a92d7c748ae825cbc1ee41a89bb1c3db05b5578ed3cfcfd7cb"},
{file = "regex-2023.10.3-cp37-cp37m-win32.whl", hash = "sha256:ce615c92d90df8373d9e13acddd154152645c0dc060871abf6bd43809673d20a"},
{file = "regex-2023.10.3-cp37-cp37m-win_amd64.whl", hash = "sha256:0f649fa32fe734c4abdfd4edbb8381c74abf5f34bc0b3271ce687b23729299ed"},
{file = "regex-2023.10.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9b98b7681a9437262947f41c7fac567c7e1f6eddd94b0483596d320092004533"},
{file = "regex-2023.10.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:91dc1d531f80c862441d7b66c4505cd6ea9d312f01fb2f4654f40c6fdf5cc37a"},
{file = "regex-2023.10.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:82fcc1f1cc3ff1ab8a57ba619b149b907072e750815c5ba63e7aa2e1163384a4"},
{file = "regex-2023.10.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7979b834ec7a33aafae34a90aad9f914c41fd6eaa8474e66953f3f6f7cbd4368"},
{file = "regex-2023.10.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ef71561f82a89af6cfcbee47f0fabfdb6e63788a9258e913955d89fdd96902ab"},
{file = "regex-2023.10.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd829712de97753367153ed84f2de752b86cd1f7a88b55a3a775eb52eafe8a94"},
{file = "regex-2023.10.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:00e871d83a45eee2f8688d7e6849609c2ca2a04a6d48fba3dff4deef35d14f07"},
{file = "regex-2023.10.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:706e7b739fdd17cb89e1fbf712d9dc21311fc2333f6d435eac2d4ee81985098c"},
{file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:cc3f1c053b73f20c7ad88b0d1d23be7e7b3901229ce89f5000a8399746a6e039"},
{file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:6f85739e80d13644b981a88f529d79c5bdf646b460ba190bffcaf6d57b2a9863"},
{file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:741ba2f511cc9626b7561a440f87d658aabb3d6b744a86a3c025f866b4d19e7f"},
{file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:e77c90ab5997e85901da85131fd36acd0ed2221368199b65f0d11bca44549711"},
{file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:979c24cbefaf2420c4e377ecd1f165ea08cc3d1fbb44bdc51bccbbf7c66a2cb4"},
{file = "regex-2023.10.3-cp38-cp38-win32.whl", hash = "sha256:58837f9d221744d4c92d2cf7201c6acd19623b50c643b56992cbd2b745485d3d"},
{file = "regex-2023.10.3-cp38-cp38-win_amd64.whl", hash = "sha256:c55853684fe08d4897c37dfc5faeff70607a5f1806c8be148f1695be4a63414b"},
{file = "regex-2023.10.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2c54e23836650bdf2c18222c87f6f840d4943944146ca479858404fedeb9f9af"},
{file = "regex-2023.10.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:69c0771ca5653c7d4b65203cbfc5e66db9375f1078689459fe196fe08b7b4930"},
{file = "regex-2023.10.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ac965a998e1388e6ff2e9781f499ad1eaa41e962a40d11c7823c9952c77123e"},
{file = "regex-2023.10.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1c0e8fae5b27caa34177bdfa5a960c46ff2f78ee2d45c6db15ae3f64ecadde14"},
{file = "regex-2023.10.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6c56c3d47da04f921b73ff9415fbaa939f684d47293f071aa9cbb13c94afc17d"},
{file = "regex-2023.10.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ef1e014eed78ab650bef9a6a9cbe50b052c0aebe553fb2881e0453717573f52"},
{file = "regex-2023.10.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d29338556a59423d9ff7b6eb0cb89ead2b0875e08fe522f3e068b955c3e7b59b"},
{file = "regex-2023.10.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:9c6d0ced3c06d0f183b73d3c5920727268d2201aa0fe6d55c60d68c792ff3588"},
{file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:994645a46c6a740ee8ce8df7911d4aee458d9b1bc5639bc968226763d07f00fa"},
{file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:66e2fe786ef28da2b28e222c89502b2af984858091675044d93cb50e6f46d7af"},
{file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:11175910f62b2b8c055f2b089e0fedd694fe2be3941b3e2633653bc51064c528"},
{file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:06e9abc0e4c9ab4779c74ad99c3fc10d3967d03114449acc2c2762ad4472b8ca"},
{file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:fb02e4257376ae25c6dd95a5aec377f9b18c09be6ebdefa7ad209b9137b73d48"},
{file = "regex-2023.10.3-cp39-cp39-win32.whl", hash = "sha256:3b2c3502603fab52d7619b882c25a6850b766ebd1b18de3df23b2f939360e1bd"},
{file = "regex-2023.10.3-cp39-cp39-win_amd64.whl", hash = "sha256:adbccd17dcaff65704c856bd29951c58a1bd4b2b0f8ad6b826dbd543fe740988"},
{file = "regex-2023.10.3.tar.gz", hash = "sha256:3fef4f844d2290ee0ba57addcec17eec9e3df73f10a2748485dfd6a3a188cc0f"},
]
[[package]]
name = "ruff"
version = "0.1.6"
description = "An extremely fast Python linter and code formatter, written in Rust."
category = "dev"
optional = false
python-versions = ">=3.7"
files = [
{file = "ruff-0.1.6-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:88b8cdf6abf98130991cbc9f6438f35f6e8d41a02622cc5ee130a02a0ed28703"},
{file = "ruff-0.1.6-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:5c549ed437680b6105a1299d2cd30e4964211606eeb48a0ff7a93ef70b902248"},
{file = "ruff-0.1.6-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1cf5f701062e294f2167e66d11b092bba7af6a057668ed618a9253e1e90cfd76"},
{file = "ruff-0.1.6-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:05991ee20d4ac4bb78385360c684e4b417edd971030ab12a4fbd075ff535050e"},
{file = "ruff-0.1.6-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:87455a0c1f739b3c069e2f4c43b66479a54dea0276dd5d4d67b091265f6fd1dc"},
{file = "ruff-0.1.6-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:683aa5bdda5a48cb8266fcde8eea2a6af4e5700a392c56ea5fb5f0d4bfdc0240"},
{file = "ruff-0.1.6-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:137852105586dcbf80c1717facb6781555c4e99f520c9c827bd414fac67ddfb6"},
{file = "ruff-0.1.6-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bd98138a98d48a1c36c394fd6b84cd943ac92a08278aa8ac8c0fdefcf7138f35"},
{file = "ruff-0.1.6-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3a0cd909d25f227ac5c36d4e7e681577275fb74ba3b11d288aff7ec47e3ae745"},
{file = "ruff-0.1.6-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:e8fd1c62a47aa88a02707b5dd20c5ff20d035d634aa74826b42a1da77861b5ff"},
{file = "ruff-0.1.6-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:fd89b45d374935829134a082617954120d7a1470a9f0ec0e7f3ead983edc48cc"},
{file = "ruff-0.1.6-py3-none-musllinux_1_2_i686.whl", hash = "sha256:491262006e92f825b145cd1e52948073c56560243b55fb3b4ecb142f6f0e9543"},
{file = "ruff-0.1.6-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:ea284789861b8b5ca9d5443591a92a397ac183d4351882ab52f6296b4fdd5462"},
{file = "ruff-0.1.6-py3-none-win32.whl", hash = "sha256:1610e14750826dfc207ccbcdd7331b6bd285607d4181df9c1c6ae26646d6848a"},
{file = "ruff-0.1.6-py3-none-win_amd64.whl", hash = "sha256:4558b3e178145491e9bc3b2ee3c4b42f19d19384eaa5c59d10acf6e8f8b57e33"},
{file = "ruff-0.1.6-py3-none-win_arm64.whl", hash = "sha256:03910e81df0d8db0e30050725a5802441c2022ea3ae4fe0609b76081731accbc"},
{file = "ruff-0.1.6.tar.gz", hash = "sha256:1b09f29b16c6ead5ea6b097ef2764b42372aebe363722f1605ecbcd2b9207184"},
]
[[package]]
name = "setuptools"
version = "69.0.2"
description = "Easily download, build, install, upgrade, and uninstall Python packages"
category = "dev"
optional = false
python-versions = ">=3.8"
files = [
{file = "setuptools-69.0.2-py3-none-any.whl", hash = "sha256:1e8fdff6797d3865f37397be788a4e3cba233608e9b509382a2777d25ebde7f2"},
{file = "setuptools-69.0.2.tar.gz", hash = "sha256:735896e78a4742605974de002ac60562d286fa8051a7e2299445e8e8fbb01aa6"},
]
[package.extras]
docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (<7.2.5)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier"]
testing = ["build[virtualenv]", "filelock (>=3.4.0)", "flake8-2020", "ini2toml[lite] (>=0.9)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pip (>=19.1)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-ruff", "pytest-timeout", "pytest-xdist", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
testing-integration = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "packaging (>=23.1)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"]
[[package]]
name = "six"
version = "1.16.0"
description = "Python 2 and 3 compatibility utilities"
category = "dev"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
files = [
{file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
{file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
]
[[package]] [[package]]
name = "tomli" name = "tomli"
@ -456,6 +748,10 @@ description = "A lil' TOML parser"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [
{file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
{file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
]
[[package]] [[package]]
name = "traitlets" name = "traitlets"
@ -464,27 +760,15 @@ description = ""
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [
{file = "traitlets-5.5.0-py3-none-any.whl", hash = "sha256:1201b2c9f76097195989cdf7f65db9897593b0dfd69e4ac96016661bb6f0d30f"},
{file = "traitlets-5.5.0.tar.gz", hash = "sha256:b122f9ff2f2f6c1709dab289a05555be011c87828e911c0cf4074b85cb780a79"},
]
[package.extras] [package.extras]
docs = ["myst-parser", "pydata-sphinx-theme", "sphinx"] docs = ["myst-parser", "pydata-sphinx-theme", "sphinx"]
test = ["pre-commit", "pytest"] test = ["pre-commit", "pytest"]
[[package]]
name = "typed-ast"
version = "1.5.4"
description = "a fork of Python 2 and 3 ast modules with type comment support"
category = "dev"
optional = false
python-versions = ">=3.6"
[[package]]
name = "types-setuptools"
version = "57.4.18"
description = "Typing stubs for setuptools"
category = "dev"
optional = false
python-versions = "*"
[[package]] [[package]]
name = "typing-extensions" name = "typing-extensions"
version = "4.4.0" version = "4.4.0"
@ -492,6 +776,10 @@ description = "Backported and Experimental Type Hints for Python 3.7+"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [
{file = "typing_extensions-4.4.0-py3-none-any.whl", hash = "sha256:16fa4864408f655d35ec496218b85f79b3437c829e93320c7c9215ccfd92489e"},
{file = "typing_extensions-4.4.0.tar.gz", hash = "sha256:1511434bb92bf8dd198c12b1cc812e800d4181cfcb867674e0f8279cc93087aa"},
]
[[package]] [[package]]
name = "wcwidth" name = "wcwidth"
@ -500,73 +788,17 @@ description = "Measures the displayed width of unicode strings in a terminal"
category = "main" category = "main"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [
[[package]] {file = "wcwidth-0.2.5-py2.py3-none-any.whl", hash = "sha256:beb4802a9cebb9144e99086eff703a642a13d6a0052920003a230f3294bbe784"},
name = "zipp" {file = "wcwidth-0.2.5.tar.gz", hash = "sha256:c4d647b99872929fdb7bdcaa4fbe7f01413ed3d98077df798530e5b04f116c83"},
version = "3.10.0" ]
description = "Backport of pathlib-compatible object wrapper for zip files"
category = "dev"
optional = false
python-versions = ">=3.7"
[package.extras]
docs = ["sphinx (>=3.5)", "jaraco.packaging (>=9)", "rst.linker (>=1.9)", "furo", "jaraco.tidelift (>=1.4)"]
testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "flake8 (<5)", "pytest-cov", "pytest-enabler (>=1.3)", "jaraco.itertools", "func-timeout", "jaraco.functools", "more-itertools", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
[extras] [extras]
cjk = ["mecab-python3", "ipadic", "mecab-ko-dic", "jieba"] cjk = ["ipadic", "jieba", "mecab-ko-dic", "mecab-python3"]
jieba = ["jieba"] jieba = ["jieba"]
mecab = ["mecab-python3", "ipadic", "mecab-ko-dic"] mecab = ["ipadic", "mecab-ko-dic", "mecab-python3"]
[metadata] [metadata]
lock-version = "1.1" lock-version = "2.0"
python-versions = "^3.7" python-versions = ">= 3.8, < 4"
content-hash = "3701c1761f9f8e16cefafdfdf04e64cb436dc96cda64fc524ed9c8b8204046a6" content-hash = "c3aecf3636c5f6b3aa9472843a96a57b2fc0b3f2f36e683046eedfdf42839e32"
[metadata.files]
appnope = []
attrs = []
backcall = []
black = []
click = []
colorama = []
decorator = []
exceptiongroup = []
flake8 = []
ftfy = []
importlib-metadata = []
iniconfig = []
ipadic = []
ipython = []
jedi = []
jieba = []
langcodes = []
matplotlib-inline = []
mccabe = []
mecab-ko-dic = []
mecab-python3 = []
msgpack = []
mypy = []
mypy-extensions = []
packaging = []
parso = []
pathspec = []
pexpect = []
pickleshare = []
platformdirs = []
pluggy = []
prompt-toolkit = []
ptyprocess = []
pycodestyle = []
pyflakes = []
pygments = []
pyparsing = []
pytest = []
regex = []
tomli = []
traitlets = []
typed-ast = []
types-setuptools = []
typing-extensions = []
wcwidth = []
zipp = []

72
pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry] [tool.poetry]
name = "wordfreq" name = "wordfreq"
version = "3.0.3" version = "3.1.0"
description = "Look up the frequencies of words in many languages, based on many sources of data." description = "Look up the frequencies of words in many languages, based on many sources of data."
authors = ["Robyn Speer <rspeer@arborelia.net>"] authors = ["Robyn Speer <rspeer@arborelia.net>"]
license = "Apache-2.0" license = "Apache-2.0"
@ -8,33 +8,75 @@ readme = "README.md"
homepage = "https://github.com/rspeer/wordfreq/" homepage = "https://github.com/rspeer/wordfreq/"
[tool.poetry.dependencies] [tool.poetry.dependencies]
python = "^3.7" python = ">= 3.8, < 4"
msgpack = ">= 1.0" msgpack = "^1.0.7"
langcodes = ">= 3.0" langcodes = ">= 3.0"
regex = ">= 2021.7.6" regex = ">= 2023.10.3"
ftfy = ">= 6.1" ftfy = ">= 6.1"
mecab-python3 = {version = "^1.0.5", optional = true} mecab-python3 = { version = "^1.0.5", optional = true }
ipadic = {version = "^1.0.0", optional = true} ipadic = { version = "^1.0.0", optional = true }
mecab-ko-dic = {version = "^1.0.0", optional = true} mecab-ko-dic = { version = "^1.0.0", optional = true }
jieba = {version = ">=0.42", optional = true} jieba = { version = ">=0.42", optional = true }
locate = "^1.1.1"
[tool.poetry.dev-dependencies] [tool.poetry.group.dev.dependencies]
pytest = "^7.2.0" pytest = "^7.2.0"
mecab-python3 = "^1.0.4" mecab-python3 = "^1.0.5"
jieba = ">= 0.42" jieba = "^0.42.1"
ipadic = "^1.0.0" ipadic = "^1.0.0"
mecab-ko-dic = "^1.0.0" mecab-ko-dic = "^1.0.0"
ipython = ">=7" ipython = ">=7"
black = "^22.1.0" mypy = "^1.7.0"
flake8 = "^4.0.1" ruff = "^0.1.6"
types-setuptools = "^57.4.9" setuptools = "^69.0.2" # implicit dependency in jieba
mypy = "^0.931" pytest-profiling = "^1.7.0"
[tool.poetry.extras] [tool.poetry.extras]
cjk = ["mecab-python3", "ipadic", "mecab-ko-dic", "jieba"] cjk = ["mecab-python3", "ipadic", "mecab-ko-dic", "jieba"]
mecab = ["mecab-python3", "ipadic", "mecab-ko-dic"] mecab = ["mecab-python3", "ipadic", "mecab-ko-dic"]
jieba = ["jieba"] jieba = ["jieba"]
[tool.ruff]
# ruff is a Python linter and formatter, which reimplements black, flake8, pylint, and more
line-length = 99
show-fixes = true
src = ["src"]
target-version = "py38"
[tool.ruff.lint]
extend-select = [
"D", # docstring style
"I", # isort
"UP", # pyupgrade -- catches obsolete code patterns
"ANN", # type annotations
"ASYNC", # async code checks
"B", # flake8-bugbear -- catches bug-prone usage
"C4", # list comprehensions
"FA", # correct use of `from __future__ import annotations`
"INP", # checks for presence of __init__.py
"T20", # print statements
"TID", # tidy imports
"PTH", # use pathlib instead of os.path
"PLE", # pylint errors
]
ignore = [
"D100", # modules without top-of-module docstrings are okay
"D104", # __init__.py doesn't need a docstring
"D107", # __init__ method doesn't need a docstring
"D2", # don't check whitespace in docstrings
"D4", # don't check grammar and style in docstrings
"E501", # long lines after auto-formatting, such as long strings, are okay
"ANN002", # we don't demand a type on *args, particularly because it's difficult to specify
"ANN003", # we don't demand a type on **kwargs, particularly because it's difficult to specify
"ANN101", # self does not need a type
"ANN102", # `cls` in classmethod does not need a type
"PTH123", # we don't need to construct a Path just to open a file by filename
]
[tool.ruff.lint.per-file-ignores]
# We are less strict about test code
"tests/**" = ["D", "ANN", "T20", "INP"]
[build-system] [build-system]
requires = ["poetry-core>=1.0.0"] requires = ["poetry-core>=1.0.0"]
build-backend = "poetry.core.masonry.api" build-backend = "poetry.core.masonry.api"

2
tests/test_apostrophes.py
View File

@ -1,4 +1,4 @@
from wordfreq import tokenize, word_frequency from wordfreq import tokenize
def test_apostrophes(): def test_apostrophes():

2
tests/test_at_sign.py
View File

@ -1,4 +1,4 @@
from wordfreq import tokenize, lossy_tokenize, word_frequency from wordfreq import lossy_tokenize, tokenize, word_frequency
def test_gender_neutral_at(): def test_gender_neutral_at():

2
tests/test_chinese.py
View File

@ -1,5 +1,5 @@
from wordfreq import tokenize, word_frequency, zipf_frequency
import pytest import pytest
from wordfreq import tokenize, word_frequency, zipf_frequency
def test_tokens(): def test_tokens():

45
tests/test_general.py
View File

@ -1,14 +1,14 @@
import pytest
from wordfreq import ( from wordfreq import (
word_frequency,
available_languages, available_languages,
cB_to_freq, cB_to_freq,
top_n_list,
random_words,
random_ascii_words,
tokenize,
lossy_tokenize, lossy_tokenize,
random_ascii_words,
random_words,
tokenize,
top_n_list,
word_frequency,
) )
import pytest
def test_freq_examples(): def test_freq_examples():
@ -142,9 +142,17 @@ def test_tokenization():
"see", "see",
] ]
assert tokenize( assert tokenize("I don't split at apostrophes, you see.", "en", include_punctuation=True) == [
"I don't split at apostrophes, you see.", "en", include_punctuation=True "i",
) == ["i", "don't", "split", "at", "apostrophes", ",", "you", "see", "."] "don't",
"split",
"at",
"apostrophes",
",",
"you",
"see",
".",
]
# Certain punctuation does not inherently split a word. # Certain punctuation does not inherently split a word.
assert tokenize("Anything is possible at zombo.com", "en") == [ assert tokenize("Anything is possible at zombo.com", "en") == [
@ -158,17 +166,20 @@ def test_tokenization():
# Splits occur after symbols, and at splitting punctuation such as hyphens. # Splits occur after symbols, and at splitting punctuation such as hyphens.
assert tokenize("😂test", "en") == ["😂", "test"] assert tokenize("😂test", "en") == ["😂", "test"]
assert tokenize("flip-flop", "en") == ["flip", "flop"] assert tokenize("flip-flop", "en") == ["flip", "flop"]
assert tokenize( assert tokenize("this text has... punctuation :)", "en", include_punctuation=True) == [
"this text has... punctuation :)", "en", include_punctuation=True "this",
) == ["this", "text", "has", "...", "punctuation", ":)"] "text",
"has",
"...",
"punctuation",
":)",
]
# Multi-codepoint emoji sequences such as 'medium-skinned woman with headscarf' # Multi-codepoint emoji sequences such as 'medium-skinned woman with headscarf'
# and 'David Bowie' stay together, because our Unicode segmentation algorithm # and 'David Bowie' stay together, because our Unicode segmentation algorithm
# is up to date # is up to date
assert tokenize("emoji test 🧕🏽", "en") == ["emoji", "test", "🧕🏽"] assert tokenize("emoji test 🧕🏽", "en") == ["emoji", "test", "🧕🏽"]
assert tokenize( assert tokenize("👨‍🎤 Planet Earth is blue, and there's nothing I can do 🌎🚀", "en") == [
"👨‍🎤 Planet Earth is blue, and there's nothing I can do 🌎🚀", "en"
) == [
"👨‍🎤", "👨‍🎤",
"planet", "planet",
"earth", "earth",
@ -221,9 +232,7 @@ def test_uncurl_quotes():
def test_phrase_freq(): def test_phrase_freq():
ff = word_frequency("flip-flop", "en") ff = word_frequency("flip-flop", "en")
assert ff > 0 assert ff > 0
phrase_freq = 1.0 / word_frequency("flip", "en") + 1.0 / word_frequency( phrase_freq = 1.0 / word_frequency("flip", "en") + 1.0 / word_frequency("flop", "en")
"flop", "en"
)
assert 1.0 / ff == pytest.approx(phrase_freq, rel=0.01) assert 1.0 / ff == pytest.approx(phrase_freq, rel=0.01)

2
tests/test_japanese.py
View File

@ -1,5 +1,5 @@
from wordfreq import tokenize, simple_tokenize, word_frequency
import pytest import pytest
from wordfreq import simple_tokenize, tokenize, word_frequency
def test_tokens(): def test_tokens():

2
tests/test_korean.py
View File

@ -1,5 +1,5 @@
from wordfreq import tokenize, word_frequency
import pytest import pytest
from wordfreq import tokenize, word_frequency
def test_tokens(): def test_tokens():

2
tests/test_numbers.py
View File

@ -1,6 +1,6 @@
from pytest import approx
from wordfreq import word_frequency from wordfreq import word_frequency
from wordfreq.numbers import digit_freq, smash_numbers from wordfreq.numbers import digit_freq, smash_numbers
from pytest import approx
def test_number_smashing(): def test_number_smashing():

61
wordfreq/__init__.py
View File

@ -1,25 +1,28 @@
from pkg_resources import resource_filename from __future__ import annotations
from functools import lru_cache
from typing import List, Dict, Iterator, Tuple
import langcodes
import msgpack
import gzip import gzip
import itertools import itertools
import pathlib
import random
import logging import logging
import math import math
import random
import warnings import warnings
from functools import lru_cache
from typing import Iterator
import langcodes
import msgpack
from wordfreq.tokens import tokenize, simple_tokenize, lossy_tokenize
from wordfreq.language_info import get_language_info from wordfreq.language_info import get_language_info
from wordfreq.numbers import digit_freq, has_digit_sequence, smash_numbers from wordfreq.numbers import digit_freq, has_digit_sequence, smash_numbers
from wordfreq.tokens import lossy_tokenize, simple_tokenize, tokenize
from .util import data_path
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
CACHE_SIZE = 100000 CACHE_SIZE = 100000
DATA_PATH = pathlib.Path(resource_filename("wordfreq", "data")) DATA_PATH = data_path()
# We'll divide the frequency by 10 for each token boundary that was inferred. # We'll divide the frequency by 10 for each token boundary that was inferred.
# (We determined the factor of 10 empirically by looking at words in the # (We determined the factor of 10 empirically by looking at words in the
@ -35,7 +38,7 @@ tokenize = tokenize
simple_tokenize = simple_tokenize simple_tokenize = simple_tokenize
def read_cBpack(filename: str) -> List[List[str]]: def read_cBpack(filename: str) -> list[list[str]]:
""" """
Read a file from an idiosyncratic format that we use for storing Read a file from an idiosyncratic format that we use for storing
approximate word frequencies, called "cBpack". approximate word frequencies, called "cBpack".
@ -79,16 +82,12 @@ def read_cBpack(filename: str) -> List[List[str]]:
with gzip.open(filename, "rb") as infile: with gzip.open(filename, "rb") as infile:
data = msgpack.load(infile, raw=False) data = msgpack.load(infile, raw=False)
header = data[0] header = data[0]
if ( if not isinstance(header, dict) or header.get("format") != "cB" or header.get("version") != 1:
not isinstance(header, dict)
or header.get("format") != "cB"
or header.get("version") != 1
):
raise ValueError("Unexpected header: %r" % header) raise ValueError("Unexpected header: %r" % header)
return data[1:] return data[1:]
def available_languages(wordlist: str = "best") -> Dict[str, str]: def available_languages(wordlist: str = "best") -> dict[str, str]:
""" """
Given a wordlist name, return a dictionary of language codes to filenames, Given a wordlist name, return a dictionary of language codes to filenames,
representing all the languages in which that wordlist is available. representing all the languages in which that wordlist is available.
@ -114,7 +113,7 @@ def available_languages(wordlist: str = "best") -> Dict[str, str]:
@lru_cache(maxsize=None) @lru_cache(maxsize=None)
def get_frequency_list( def get_frequency_list(
lang: str, wordlist: str = "best", match_cutoff: None = None lang: str, wordlist: str = "best", match_cutoff: None = None
) -> List[List[str]]: ) -> list[list[str]]:
""" """
Read the raw data from a wordlist file, returning it as a list of Read the raw data from a wordlist file, returning it as a list of
lists. (See `read_cBpack` for what this represents.) lists. (See `read_cBpack` for what this represents.)
@ -125,19 +124,21 @@ def get_frequency_list(
Looking up the alternate code 'por' will also get the same list. Looking up the alternate code 'por' will also get the same list.
""" """
if match_cutoff is not None: if match_cutoff is not None:
warnings.warn("The `match_cutoff` parameter is deprecated", DeprecationWarning) warnings.warn(
"The `match_cutoff` parameter is deprecated", DeprecationWarning, stacklevel=2
)
available = available_languages(wordlist) available = available_languages(wordlist)
# the max_distance is high because we unify scripts, such as Traditional # the max_distance is high because we unify scripts, such as Traditional
# vs. Simplified Chinese, in one wordlist # vs. Simplified Chinese, in one wordlist
best, _distance = langcodes.closest_match(lang, list(available), max_distance=60) best, _distance = langcodes.closest_match(lang, list(available), max_distance=60)
if best == "und": if best == "und":
raise LookupError("No wordlist %r available for language %r" % (wordlist, lang)) raise LookupError(f"No wordlist {wordlist!r} available for language {lang!r}")
if best != lang: if best != lang:
logger.warning( logger.warning(
"You asked for word frequencies in language %r. Using the " f"You asked for word frequencies in language {lang!r}. Using the "
"nearest match, which is %r." % (lang, best) f"nearest match, which is {best!r}."
) )
return read_cBpack(available[best]) return read_cBpack(available[best])
@ -198,13 +199,15 @@ def freq_to_zipf(freq: float) -> float:
@lru_cache(maxsize=None) @lru_cache(maxsize=None)
def get_frequency_dict( def get_frequency_dict(
lang: str, wordlist: str = "best", match_cutoff: None = None lang: str, wordlist: str = "best", match_cutoff: None = None
) -> Dict[str, float]: ) -> dict[str, float]:
""" """
Get a word frequency list as a dictionary, mapping tokens to Get a word frequency list as a dictionary, mapping tokens to
frequencies as floating-point probabilities. frequencies as floating-point probabilities.
""" """
if match_cutoff is not None: if match_cutoff is not None:
warnings.warn("The `match_cutoff` parameter is deprecated", DeprecationWarning) warnings.warn(
"The `match_cutoff` parameter is deprecated", DeprecationWarning, stacklevel=2
)
freqs = {} freqs = {}
pack = get_frequency_list(lang, wordlist) pack = get_frequency_list(lang, wordlist)
for index, bucket in enumerate(pack): for index, bucket in enumerate(pack):
@ -229,7 +232,7 @@ def iter_wordlist(lang: str, wordlist: str = "best") -> Iterator[str]:
# This dict and inner function are used to implement a "drop everything" cache # This dict and inner function are used to implement a "drop everything" cache
# for word_frequency(); the overheads of lru_cache() are comparable to the time # for word_frequency(); the overheads of lru_cache() are comparable to the time
# it takes to look up frequencies from scratch, so something faster is needed. # it takes to look up frequencies from scratch, so something faster is needed.
_wf_cache: Dict[Tuple[str, str, str, float], float] = {} _wf_cache: dict[tuple[str, str, str, float], float] = {}
def _word_frequency(word: str, lang: str, wordlist: str, minimum: float) -> float: def _word_frequency(word: str, lang: str, wordlist: str, minimum: float) -> float:
@ -277,9 +280,7 @@ def _word_frequency(word: str, lang: str, wordlist: str, minimum: float) -> floa
return round(unrounded, leading_zeroes + 3) return round(unrounded, leading_zeroes + 3)
def word_frequency( def word_frequency(word: str, lang: str, wordlist: str = "best", minimum: float = 0.0) -> float:
word: str, lang: str, wordlist: str = "best", minimum: float = 0.0
) -> float:
""" """
Get the frequency of `word` in the language with code `lang`, from the Get the frequency of `word` in the language with code `lang`, from the
specified `wordlist`. specified `wordlist`.
@ -306,7 +307,7 @@ def word_frequency(
return _wf_cache[args] return _wf_cache[args]
def zipf_frequency(word: str, lang: str, wordlist: str = "best", minimum: float = 0.0): def zipf_frequency(word: str, lang: str, wordlist: str = "best", minimum: float = 0.0) -> float:
""" """
Get the frequency of `word`, in the language with code `lang`, on the Zipf Get the frequency of `word`, in the language with code `lang`, on the Zipf
scale. scale.
@ -334,9 +335,7 @@ def zipf_frequency(word: str, lang: str, wordlist: str = "best", minimum: float
@lru_cache(maxsize=100) @lru_cache(maxsize=100)
def top_n_list( def top_n_list(lang: str, n: int, wordlist: str = "best", ascii_only: bool = False) -> list[str]:
lang: str, n: int, wordlist: str = "best", ascii_only: bool = False
) -> List[str]:
""" """
Return a frequency list of length `n` in descending order of frequency. Return a frequency list of length `n` in descending order of frequency.
This list contains words from `wordlist`, of the given language. This list contains words from `wordlist`, of the given language.

31
wordfreq/chinese.py
View File

@ -1,21 +1,22 @@
from pkg_resources import resource_filename from __future__ import annotations
from typing import List
import jieba
import msgpack
import gzip import gzip
DICT_FILENAME = resource_filename("wordfreq", "data/jieba_zh.txt") import jieba
ORIG_DICT_FILENAME = resource_filename("wordfreq", "data/jieba_zh_orig.txt") import msgpack
SIMP_MAP_FILENAME = resource_filename("wordfreq", "data/_chinese_mapping.msgpack.gz")
from .util import data_path
DICT_FILENAME = data_path("jieba_zh.txt")
ORIG_DICT_FILENAME = data_path("jieba_zh_orig.txt")
SIMP_MAP_FILENAME = data_path("_chinese_mapping.msgpack.gz")
try: try:
SIMPLIFIED_MAP = msgpack.load( SIMPLIFIED_MAP = msgpack.load(gzip.open(SIMP_MAP_FILENAME), raw=False, strict_map_key=False)
gzip.open(SIMP_MAP_FILENAME), raw=False, strict_map_key=False
)
except TypeError: except TypeError:
# work around incompatibility between pure-Python msgpack and C msgpack # work around incompatibility between pure-Python msgpack and C msgpack
SIMPLIFIED_MAP = msgpack.load(gzip.open(SIMP_MAP_FILENAME), raw=False) SIMPLIFIED_MAP = msgpack.load(gzip.open(SIMP_MAP_FILENAME), raw=False)
jieba_tokenizer = None jieba_tokenizer: jieba.Tokenizer | None = None
jieba_orig_tokenizer = None jieba_orig_tokenizer: jieba.Tokenizer | None = None
def simplify_chinese(text: str) -> str: def simplify_chinese(text: str) -> str:
@ -32,7 +33,7 @@ def simplify_chinese(text: str) -> str:
return text.translate(SIMPLIFIED_MAP).casefold() return text.translate(SIMPLIFIED_MAP).casefold()
def jieba_tokenize(text: str, external_wordlist: bool = False) -> List[str]: def jieba_tokenize(text: str, external_wordlist: bool = False) -> list[str]:
""" """
Tokenize the given text into tokens whose word frequencies can probably Tokenize the given text into tokens whose word frequencies can probably
be looked up. This uses Jieba, a word-frequency-based tokenizer. be looked up. This uses Jieba, a word-frequency-based tokenizer.
@ -61,8 +62,6 @@ def jieba_tokenize(text: str, external_wordlist: bool = False) -> List[str]:
# those spans from the original text, even if it's in Traditional # those spans from the original text, even if it's in Traditional
# Chinese # Chinese
tokens = [] tokens = []
for _token, start, end in jieba_tokenizer.tokenize( for _token, start, end in jieba_tokenizer.tokenize(simplify_chinese(text), HMM=False):
simplify_chinese(text), HMM=False
):
tokens.append(text[start:end]) tokens.append(text[start:end])
return tokens return tokens

10
wordfreq/language_info.py
View File

@ -1,6 +1,8 @@
from __future__ import annotations
from functools import lru_cache from functools import lru_cache
from langcodes import Language, closest_match from langcodes import Language, closest_match
from typing import List, Union
# Text in scripts written without spaces has to be handled specially in our # Text in scripts written without spaces has to be handled specially in our
# tokenization regex (see TOKEN_RE in tokens.py). Also, when one of these is # tokenization regex (see TOKEN_RE in tokens.py). Also, when one of these is
@ -44,9 +46,7 @@ EXTRA_JAPANESE_CHARACTERS = "ー々〻〆"
# happens in ConceptNet. # happens in ConceptNet.
def _language_in_list( def _language_in_list(language: Language, targets: list[str], max_distance: int = 10) -> bool:
language: Language, targets: List[str], max_distance: int = 10
) -> bool:
""" """
A helper function to determine whether this language matches one of the A helper function to determine whether this language matches one of the
target languages, with a match score above a certain threshold. target languages, with a match score above a certain threshold.
@ -59,7 +59,7 @@ def _language_in_list(
@lru_cache(maxsize=None) @lru_cache(maxsize=None)
def get_language_info(language: Union[str, Language]) -> dict: def get_language_info(language: str | Language) -> dict:
""" """
Looks up the things we need to know about how to handle text in a given Looks up the things we need to know about how to handle text in a given
language. This will return a dictionary with the following fields: language. This will return a dictionary with the following fields:

15
wordfreq/mecab.py
View File

@ -1,7 +1,8 @@
import MeCab from __future__ import annotations
import unicodedata import unicodedata
from typing import Dict, List import MeCab
def make_mecab_analyzer(lang: str) -> MeCab.Tagger: def make_mecab_analyzer(lang: str) -> MeCab.Tagger:
@ -22,10 +23,10 @@ def make_mecab_analyzer(lang: str) -> MeCab.Tagger:
# The constructed analyzers will go in this dictionary. # The constructed analyzers will go in this dictionary.
MECAB_ANALYZERS: Dict[str, MeCab.Tagger] = {} MECAB_ANALYZERS: dict[str, MeCab.Tagger] = {}
def mecab_tokenize(text: str, lang: str) -> List[str]: def mecab_tokenize(text: str, lang: str) -> list[str]:
""" """
Use the mecab-python3 package to tokenize the given text. The `lang` Use the mecab-python3 package to tokenize the given text. The `lang`
must be 'ja' for Japanese or 'ko' for Korean. must be 'ja' for Japanese or 'ko' for Korean.
@ -42,8 +43,4 @@ def mecab_tokenize(text: str, lang: str) -> List[str]:
analyzed = analyzer.parse(text) analyzed = analyzer.parse(text)
if not analyzed: if not analyzed:
return [] return []
return [ return [line.split("\t")[0] for line in analyzed.split("\n") if line != "" and line != "EOS"]
line.split("\t")[0]
for line in analyzed.split("\n")
if line != "" and line != "EOS"
]

5
wordfreq/preprocess.py
View File

@ -1,9 +1,10 @@
import regex
import unicodedata import unicodedata
import regex
from langcodes import Language
from .language_info import get_language_info from .language_info import get_language_info
from .transliterate import transliterate from .transliterate import transliterate
from langcodes import Language
MARK_RE = regex.compile(r"[\p{Mn}\N{ARABIC TATWEEL}]", regex.V1) MARK_RE = regex.compile(r"[\p{Mn}\N{ARABIC TATWEEL}]", regex.V1)

46
wordfreq/tokens.py
View File

@ -1,31 +1,31 @@
import regex from __future__ import annotations
import unicodedata
import logging import logging
import unicodedata
import langcodes import langcodes
from typing import List import regex
from ftfy.fixes import uncurl_quotes from ftfy.fixes import uncurl_quotes
from .language_info import ( from .language_info import (
get_language_info,
SPACELESS_SCRIPTS,
EXTRA_JAPANESE_CHARACTERS, EXTRA_JAPANESE_CHARACTERS,
SPACELESS_SCRIPTS,
get_language_info,
) )
from .preprocess import preprocess_text from .preprocess import preprocess_text
# Placeholders for CJK functions that we'll import on demand # Placeholders for CJK functions that we'll import on demand
_mecab_tokenize = None _mecab_tokenize = None # type: ignore
_jieba_tokenize = None _jieba_tokenize = None # type: ignore
_simplify_chinese = None _simplify_chinese = None # type: ignore
_WARNED_LANGUAGES = set() _WARNED_LANGUAGES: set[str] = set()
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
def _make_spaceless_expr() -> str: def _make_spaceless_expr() -> str:
scripts = sorted(SPACELESS_SCRIPTS) scripts = sorted(SPACELESS_SCRIPTS)
pieces = [r"\p{IsIdeo}"] + [ pieces = [r"\p{IsIdeo}"] + [r"\p{Script=%s}" % script_code for script_code in scripts]
r"\p{Script=%s}" % script_code for script_code in scripts
]
return "".join(pieces) + EXTRA_JAPANESE_CHARACTERS return "".join(pieces) + EXTRA_JAPANESE_CHARACTERS
@ -148,11 +148,7 @@ TOKEN_RE = regex.compile(
# part of the token in Case 3. # part of the token in Case 3.
\w\w?' \w\w?'
""".replace( """.replace("<SPACELESS>", SPACELESS_EXPR).replace("<VOWEL>", INITIAL_VOWEL_EXPR),
"<SPACELESS>", SPACELESS_EXPR
).replace(
"<VOWEL>", INITIAL_VOWEL_EXPR
),
regex.V1 | regex.WORD | regex.VERBOSE, regex.V1 | regex.WORD | regex.VERBOSE,
) )
@ -167,11 +163,7 @@ TOKEN_RE_WITH_PUNCTUATION = regex.compile(
(?=[\w\p{So}]) (?!\w\w?'<VOWEL>) (?=[\w\p{So}]) (?!\w\w?'<VOWEL>)
\X+? (?: @s? (?!w) | \b) | # Case 3 \X+? (?: @s? (?!w) | \b) | # Case 3
\w\w?' # Case 4 \w\w?' # Case 4
""".replace( """.replace("<SPACELESS>", SPACELESS_EXPR).replace("<VOWEL>", INITIAL_VOWEL_EXPR),
"<SPACELESS>", SPACELESS_EXPR
).replace(
"<VOWEL>", INITIAL_VOWEL_EXPR
),
regex.V1 | regex.WORD | regex.VERBOSE, regex.V1 | regex.WORD | regex.VERBOSE,
) )
@ -180,7 +172,7 @@ TOKEN_RE_WITH_PUNCTUATION = regex.compile(
PUNCT_RE = regex.compile(r"[\p{punct}]+") PUNCT_RE = regex.compile(r"[\p{punct}]+")
def simple_tokenize(text: str, include_punctuation: bool = False) -> List[str]: def simple_tokenize(text: str, include_punctuation: bool = False) -> list[str]:
""" """
Tokenize the given text using a straightforward, Unicode-aware token Tokenize the given text using a straightforward, Unicode-aware token
expression. expression.
@ -220,7 +212,7 @@ def tokenize(
lang: str, lang: str,
include_punctuation: bool = False, include_punctuation: bool = False,
external_wordlist: bool = False, external_wordlist: bool = False,
) -> List[str]: ) -> list[str]:
""" """
Tokenize this text in a way that's relatively simple but appropriate for Tokenize this text in a way that's relatively simple but appropriate for
the language. Strings that are looked up in wordfreq will be run through the language. Strings that are looked up in wordfreq will be run through
@ -286,9 +278,7 @@ def tokenize(
if info["tokenizer"] != "regex" and lang not in _WARNED_LANGUAGES: if info["tokenizer"] != "regex" and lang not in _WARNED_LANGUAGES:
logger.warning( logger.warning(
"The language '{}' is in the '{}' script, which we don't " "The language '{}' is in the '{}' script, which we don't "
"have a tokenizer for. The results will be bad.".format( "have a tokenizer for. The results will be bad.".format(lang, info["script"])
lang, info["script"]
)
) )
_WARNED_LANGUAGES.add(lang) _WARNED_LANGUAGES.add(lang)
tokens = simple_tokenize(text, include_punctuation=include_punctuation) tokens = simple_tokenize(text, include_punctuation=include_punctuation)
@ -301,7 +291,7 @@ def lossy_tokenize(
lang: str, lang: str,
include_punctuation: bool = False, include_punctuation: bool = False,
external_wordlist: bool = False, external_wordlist: bool = False,
) -> List[str]: ) -> list[str]:
""" """
Get a list of tokens for this text, with largely the same results and Get a list of tokens for this text, with largely the same results and
options as `tokenize`, but aggressively normalize some text in a lossy way options as `tokenize`, but aggressively normalize some text in a lossy way

212
wordfreq/transliterate.py
View File

@ -1,96 +1,156 @@
from __future__ import annotations
# This table comes from # This table comes from
# https://github.com/opendatakosovo/cyrillic-transliteration/blob/master/cyrtranslit/mapping.py, # https://github.com/opendatakosovo/cyrillic-transliteration/blob/master/cyrtranslit/mapping.py,
# from the 'cyrtranslit' module. We originally had to reimplement it because # from the 'cyrtranslit' module. We originally had to reimplement it because
# 'cyrtranslit' didn't work in Python 3; now it does, but we've made the table # 'cyrtranslit' didn't work in Python 3; now it does, but we've made the table
# more robust than the one in cyrtranslit. # more robust than the one in cyrtranslit.
SR_LATN_TABLE = { SR_LATN_TABLE = {
ord('А'): 'A', ord('а'): 'a', ord("А"): "A",
ord('Б'): 'B', ord('б'): 'b', ord("а"): "a",
ord('В'): 'V', ord('в'): 'v', ord("Б"): "B",
ord('Г'): 'G', ord('г'): 'g', ord("б"): "b",
ord('Д'): 'D', ord('д'): 'd', ord("В"): "V",
ord('Ђ'): 'Đ', ord('ђ'): 'đ', ord("в"): "v",
ord('Е'): 'E', ord('е'): 'e', ord("Г"): "G",
ord('Ж'): 'Ž', ord('ж'): 'ž', ord("г"): "g",
ord('З'): 'Z', ord('з'): 'z', ord("Д"): "D",
ord('И'): 'I', ord('и'): 'i', ord("д"): "d",
ord('Ј'): 'J', ord('ј'): 'j', ord("Ђ"): "Đ",
ord('К'): 'K', ord('к'): 'k', ord("ђ"): "đ",
ord('Л'): 'L', ord('л'): 'l', ord("Е"): "E",
ord('Љ'): 'Lj', ord('љ'): 'lj', ord("е"): "e",
ord('М'): 'M', ord('м'): 'm', ord("Ж"): "Ž",
ord('Н'): 'N', ord('н'): 'n', ord("ж"): "ž",
ord('Њ'): 'Nj', ord('њ'): 'nj', ord("З"): "Z",
ord('О'): 'O', ord('о'): 'o', ord("з"): "z",
ord('П'): 'P', ord('п'): 'p', ord("И"): "I",
ord('Р'): 'R', ord('р'): 'r', ord("и"): "i",
ord('С'): 'S', ord('с'): 's', ord("Ј"): "J",
ord('Т'): 'T', ord('т'): 't', ord("ј"): "j",
ord('Ћ'): 'Ć', ord('ћ'): 'ć', ord("К"): "K",
ord('У'): 'U', ord('у'): 'u', ord("к"): "k",
ord('Ф'): 'F', ord('ф'): 'f', ord("Л"): "L",
ord('Х'): 'H', ord('х'): 'h', ord("л"): "l",
ord('Ц'): 'C', ord('ц'): 'c', ord("Љ"): "Lj",
ord('Ч'): 'Č', ord('ч'): 'č', ord("љ"): "lj",
ord('Џ'): 'Dž', ord('џ'): 'dž', ord("М"): "M",
ord('Ш'): 'Š', ord('ш'): 'š', ord("м"): "m",
ord("Н"): "N",
ord("н"): "n",
ord("Њ"): "Nj",
ord("њ"): "nj",
ord("О"): "O",
ord("о"): "o",
ord("П"): "P",
ord("п"): "p",
ord("Р"): "R",
ord("р"): "r",
ord("С"): "S",
ord("с"): "s",
ord("Т"): "T",
ord("т"): "t",
ord("Ћ"): "Ć",
ord("ћ"): "ć",
ord("У"): "U",
ord("у"): "u",
ord("Ф"): "F",
ord("ф"): "f",
ord("Х"): "H",
ord("х"): "h",
ord("Ц"): "C",
ord("ц"): "c",
ord("Ч"): "Č",
ord("ч"): "č",
ord("Џ"): "Dž",
ord("џ"): "dž",
ord("Ш"): "Š",
ord("ш"): "š",
# Handle Cyrillic letters from other languages. We hope these cases don't # Handle Cyrillic letters from other languages. We hope these cases don't
# come up often when we're trying to transliterate Serbian, but if these # come up often when we're trying to transliterate Serbian, but if these
# letters show up in loan-words or code-switching text, we can at least # letters show up in loan-words or code-switching text, we can at least
# transliterate them approximately instead of leaving them as Cyrillic # transliterate them approximately instead of leaving them as Cyrillic
# letters surrounded by Latin. # letters surrounded by Latin.
# Russian letters # Russian letters
ord('Ё'): 'Jo', ord('ё'): 'jo', ord("Ё"): "Jo",
ord('Й'): 'J', ord('й'): 'j', ord("ё"): "jo",
ord('Щ'): 'Šč', ord('щ'): 'šč', ord("Й"): "J",
ord('Ъ'): '', ord('ъ'): '', ord("й"): "j",
ord('Ы'): 'Y', ord('ы'): 'y', ord("Щ"): "Šč",
ord('Ь'): "'", ord('ь'): "'", ord("щ"): "šč",
ord('Э'): 'E', ord('э'): 'e', ord("Ъ"): "",
ord('Ю'): 'Ju', ord('ю'): 'ju', ord("ъ"): "",
ord('Я'): 'Ja', ord('я'): 'ja', ord("Ы"): "Y",
ord("ы"): "y",
ord("Ь"): "'",
ord("ь"): "'",
ord("Э"): "E",
ord("э"): "e",
ord("Ю"): "Ju",
ord("ю"): "ju",
ord("Я"): "Ja",
ord("я"): "ja",
# Belarusian letter # Belarusian letter
ord('Ў'): 'Ŭ', ord('ў'): 'ŭ', ord("Ў"): "Ŭ",
ord("ў"): "ŭ",
# Ukrainian letters # Ukrainian letters
ord('Є'): 'Je', ord('є'): 'je', ord("Є"): "Je",
ord('І'): 'I', ord('і'): 'i', ord("є"): "je",
ord('Ї'): 'Ï', ord('ї'): 'ï', ord("І"): "I",
ord('Ґ'): 'G', ord('ґ'): 'g', ord("і"): "i",
ord("Ї"): "Ï",
ord("ї"): "ï",
ord("Ґ"): "G",
ord("ґ"): "g",
# Macedonian letters # Macedonian letters
ord('Ѕ'): 'Dz', ord('ѕ'): 'dz', ord("Ѕ"): "Dz",
ord('Ѓ'): 'Ǵ', ord('ѓ'): 'ǵ', ord("ѕ"): "dz",
ord('Ќ'): 'Ḱ', ord('ќ'): 'ḱ', ord("Ѓ"): "Ǵ",
ord("ѓ"): "ǵ",
ord("Ќ"): "Ḱ",
ord("ќ"): "ḱ",
} }
AZ_LATN_TABLE = SR_LATN_TABLE.copy() AZ_LATN_TABLE = SR_LATN_TABLE.copy()
AZ_LATN_TABLE.update({ AZ_LATN_TABLE.update(
# Distinct Azerbaijani letters {
ord('Ҹ'): 'C', ord('ҹ'): 'c', # Distinct Azerbaijani letters
ord('Ә'): 'Ə', ord('ә'): 'ə', ord("Ҹ"): "C",
ord('Ғ'): 'Ğ', ord('ғ'): 'ğ', ord("ҹ"): "c",
ord('Һ'): 'H', ord('һ'): 'h', ord("Ә"): "Ə",
ord('Ө'): 'Ö', ord('ө'): 'ö', ord("ә"): "ə",
ord('Ҝ'): 'G', ord('ҝ'): 'g', ord("Ғ"): "Ğ",
ord('Ү'): 'Ü', ord('ү'): 'ü', ord("ғ"): "ğ",
ord("Һ"): "H",
# Azerbaijani letters with different transliterations ord("һ"): "h",
ord('Ч'): 'Ç', ord('ч'): 'ç', ord("Ө"): "Ö",
ord('Х'): 'X', ord('х'): 'x', ord("ө"): "ö",
ord('Ы'): 'I', ord('ы'): 'ı', ord("Ҝ"): "G",
ord('И'): 'İ', ord('и'): 'i', ord("ҝ"): "g",
ord('Ж'): 'J', ord('ж'): 'j', ord("Ү"): "Ü",
ord('Ј'): 'Y', ord('ј'): 'y', ord("ү"): "ü",
ord('Г'): 'Q', ord('г'): 'q', # Azerbaijani letters with different transliterations
ord('Ш'): 'Ş', ord('ш'): 'ş', ord("Ч"): "Ç",
}) ord("ч"): "ç",
ord("Х"): "X",
ord("х"): "x",
ord("Ы"): "I",
ord("ы"): "ı",
ord("И"): "İ",
ord("и"): "i",
ord("Ж"): "J",
ord("ж"): "j",
ord("Ј"): "Y",
ord("ј"): "y",
ord("Г"): "Q",
ord("г"): "q",
ord("Ш"): "Ş",
ord("ш"): "ş",
}
)
def transliterate(table, text): def transliterate(table: dict[int, str], text: str) -> str:
""" """
Transliterate text according to one of the tables above. Transliterate text according to one of the tables above.
@ -101,9 +161,9 @@ def transliterate(table, text):
Latin alphabet. Latin alphabet.
- 'az-Latn' means the same for Azerbaijani Cyrillic to Latn. - 'az-Latn' means the same for Azerbaijani Cyrillic to Latn.
""" """
if table == 'sr-Latn': if table == "sr-Latn":
return text.translate(SR_LATN_TABLE) return text.translate(SR_LATN_TABLE)
elif table == 'az-Latn': elif table == "az-Latn":
return text.translate(AZ_LATN_TABLE) return text.translate(AZ_LATN_TABLE)
else: else:
raise ValueError("Unknown transliteration table: {!r}".format(table)) raise ValueError(f"Unknown transliteration table: {table!r}")

15
wordfreq/util.py Normal file
View File

@ -0,0 +1,15 @@
from __future__ import annotations
from pathlib import Path
import locate
def data_path(filename: str | None = None) -> Path:
"""
Get a path to a file in the data directory.
"""
if filename is None:
return Path(locate.this_dir(), "data")
else:
return Path(locate.this_dir(), "data", filename)