Format

* add download url

* Update .pre-commit-config.yaml

* Update cli.mdx

---------

Co-authored-by: ebonnafoux <etienne.bonnafoux@gmail.com>

.github/workflows/cibuildwheel.yml

@@ -9,91 +9,13 @@ on:
       - 'prerelease-v[0-9]+.[0-9]+.[0-9]+**'
 jobs:
   build_wheels:
-    name: Build wheels on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        # macos-13 is an intel runner, macos-14 is apple silicon
-        os: [ubuntu-latest, windows-latest, macos-13, macos-14]
-
-    steps:
-      - uses: actions/checkout@v4
-      # aarch64 (arm) is built via qemu emulation
-      # QEMU is sadly too slow. We need to wait for public ARM support
-      #- name: Set up QEMU
-      #  if: runner.os == 'Linux'
-      #  uses: docker/setup-qemu-action@v3
-      #  with:
-      #    platforms: all
-      - name: Build wheels
-        uses: pypa/cibuildwheel@v2.19.1
-        env:
-          CIBW_ARCHS_LINUX: auto
-        with:
-          package-dir: .
-          output-dir: wheelhouse
-          config-file: "{package}/pyproject.toml"
-      - uses: actions/upload-artifact@v4
-        with:
-          name: cibw-wheels-${{ matrix.os }}-${{ strategy.job-index }}
-          path: ./wheelhouse/*.whl
-
-  build_sdist:
-    name: Build source distribution
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Build sdist
-        run: pipx run build --sdist
-      - uses: actions/upload-artifact@v4
-        with:
-          name: cibw-sdist
-          path: dist/*.tar.gz
-  create_release:
-    needs: [build_wheels, build_sdist]
-    runs-on: ubuntu-latest
+    uses: explosion/gha-cibuildwheel/.github/workflows/cibuildwheel.yml@main
     permissions:
       contents: write
-      checks: write
       actions: read
-      issues: read
-      packages: write
-      pull-requests: read
-      repository-projects: read
-      statuses: read
-    steps:
-      - name: Get the tag name and determine if it's a prerelease
-        id: get_tag_info
-        run: |
-          FULL_TAG=${GITHUB_REF#refs/tags/}
-          if [[ $FULL_TAG == release-* ]]; then
-            TAG_NAME=${FULL_TAG#release-}
-            IS_PRERELEASE=false
-          elif [[ $FULL_TAG == prerelease-* ]]; then
-            TAG_NAME=${FULL_TAG#prerelease-}
-            IS_PRERELEASE=true
-          else
-            echo "Tag does not match expected patterns" >&2
-            exit 1
-          fi
-          echo "FULL_TAG=$TAG_NAME" >> $GITHUB_ENV
-          echo "TAG_NAME=$TAG_NAME" >> $GITHUB_ENV
-          echo "IS_PRERELEASE=$IS_PRERELEASE" >> $GITHUB_ENV
-      - uses: actions/download-artifact@v4
-        with:
-          # unpacks all CIBW artifacts into dist/
-          pattern: cibw-*
-          path: dist
-          merge-multiple: true
-      - name: Create Draft Release
-        id: create_release
-        uses: softprops/action-gh-release@v2
-        if: startsWith(github.ref, 'refs/tags/')
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          name: ${{ env.TAG_NAME }}
-          draft: true
-          prerelease: ${{ env.IS_PRERELEASE }}
-          files: "./dist/*" 
+    with:
+      wheel-name-pattern: "spacy-*.whl"
+      pure-python: false
+    secrets:
+      gh-token: ${{ secrets.GITHUB_TOKEN }}
+

.github/workflows/tests.yml

@@ -45,11 +45,12 @@ jobs:
         run: |
           python -m pip install flake8==5.0.4
           python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics
-      - name: cython-lint
-        run: |
-          python -m pip install cython-lint -c requirements.txt
-          # E501: line too log, W291: trailing whitespace, E266: too many leading '#' for block comment
-          cython-lint spacy --ignore E501,W291,E266
+          # Unfortunately cython-lint isn't working after the shift to Cython 3.
+          #- name: cython-lint
+          #  run: |
+          #    python -m pip install cython-lint -c requirements.txt
+          #    # E501: line too log, W291: trailing whitespace, E266: too many leading '#' for block comment
+          #    cython-lint spacy --ignore E501,W291,E266
 
   tests:
     name: Test
@@ -58,7 +59,7 @@ jobs:
       fail-fast: true
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python_version: ["3.9", "3.11", "3.12"]
+        python_version: ["3.10", "3.11", "3.12", "3.13"]
 
     runs-on: ${{ matrix.os }}
 

CONTRIBUTING.md

@@ -449,8 +449,8 @@ and plugins in spaCy v3.0, and we can't wait to see what you build with it!
   [`spacy`](https://github.com/topics/spacy?o=desc&s=stars) and
   [`spacy-extensions`](https://github.com/topics/spacy-extension?o=desc&s=stars)
   to make it easier to find. Those are also the topics we're linking to from the
-  spaCy website. If you're sharing your project on Twitter, feel free to tag
-  [@spacy_io](https://twitter.com/spacy_io) so we can check it out.
+  spaCy website. If you're sharing your project on X, feel free to tag
+  [@spacy_io](https://x.com/spacy_io) so we can check it out.
 
 - Once your extension is published, you can open a
   [PR](https://github.com/explosion/spaCy/pulls) to suggest it for the

MANIFEST.in

@@ -4,5 +4,6 @@ include README.md
 include pyproject.toml
 include spacy/py.typed
 recursive-include spacy/cli *.yml
+recursive-include spacy/tests *.json
 recursive-include licenses *
 recursive-exclude spacy *.cpp

README.md

@@ -16,7 +16,7 @@ model packaging, deployment and workflow management. spaCy is commercial
 open-source software, released under the
 [MIT license](https://github.com/explosion/spaCy/blob/master/LICENSE).
 
-💫 **Version 3.7 out now!**
+💫 **Version 3.8 out now!**
 [Check out the release notes here.](https://github.com/explosion/spaCy/releases)
 
 [![tests](https://github.com/explosion/spaCy/actions/workflows/tests.yml/badge.svg)](https://github.com/explosion/spaCy/actions/workflows/tests.yml)
@@ -28,7 +28,6 @@ open-source software, released under the
 <br />
 [![PyPi downloads](https://static.pepy.tech/personalized-badge/spacy?period=total&units=international_system&left_color=grey&right_color=orange&left_text=pip%20downloads)](https://pypi.org/project/spacy/)
 [![Conda downloads](https://img.shields.io/conda/dn/conda-forge/spacy?label=conda%20downloads)](https://anaconda.org/conda-forge/spacy)
-[![spaCy on Twitter](https://img.shields.io/twitter/follow/spacy_io.svg?style=social&label=Follow)](https://twitter.com/spacy_io)
 
 ## 📖 Documentation
 
@@ -47,6 +46,7 @@ open-source software, released under the
 | 👩‍🏫 **[Online Course]**                                                                                                                                                                                                    | Learn spaCy in this free and interactive online course.                                                                                                                                                                                                                                                                                      |
 | 📰 **[Blog]**                                                                                                                                                                                                             | Read about current spaCy and Prodigy development, releases, talks and more from Explosion.                                                                                                                                                                                                                 |
 | 📺 **[Videos]**                                                                                                                                                                                                           | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                                                                    |
+| 🔴 **[Live Stream]**                                                                                                                                                                                                       | Join Matt as he works on spaCy and chat about NLP, live every week.                                                                                                                                                                                                                                                                         |
 | 🛠 **[Changelog]**                                                                                                                                                                                                         | Changes and version history.                                                                                                                                                                                                                                                                                                                 |
 | 💝 **[Contribute]**                                                                                                                                                                                                       | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                                                        |
 | 👕 **[Swag]**                                                                                                                                                                                                             | Support us and our work with unique, custom-designed swag!                                                                                                                                                                                                                                                                                   |
@@ -62,6 +62,7 @@ open-source software, released under the
 [universe]: https://spacy.io/universe
 [spacy vs code extension]: https://github.com/explosion/spacy-vscode
 [videos]: https://www.youtube.com/c/ExplosionAI
+[live stream]: https://www.youtube.com/playlist?list=PLBmcuObd5An5_iAxNYLJa_xWmNzsYce8c
 [online course]: https://course.spacy.io
 [blog]: https://explosion.ai
 [project templates]: https://github.com/explosion/projects
@@ -79,13 +80,14 @@ more people can benefit from it.
 | Type                            | Platforms                               |
 | ------------------------------- | --------------------------------------- |
 | 🚨 **Bug Reports**              | [GitHub Issue Tracker]                  |
-| 🎁 **Feature Requests & Ideas** | [GitHub Discussions]                    |
+| 🎁 **Feature Requests & Ideas** | [GitHub Discussions] · [Live Stream]    |
 | 👩‍💻 **Usage Questions**          | [GitHub Discussions] · [Stack Overflow] |
-| 🗯 **General Discussion**        | [GitHub Discussions]                    |
+| 🗯 **General Discussion**        | [GitHub Discussions] · [Live Stream]   |
 
 [github issue tracker]: https://github.com/explosion/spaCy/issues
 [github discussions]: https://github.com/explosion/spaCy/discussions
 [stack overflow]: https://stackoverflow.com/questions/tagged/spacy
+[live stream]: https://www.youtube.com/playlist?list=PLBmcuObd5An5_iAxNYLJa_xWmNzsYce8c
 
 ## Features
 
@@ -115,7 +117,7 @@ For detailed installation instructions, see the
 
 - **Operating system**: macOS / OS X · Linux · Windows (Cygwin, MinGW, Visual
   Studio)
-- **Python version**: Python 3.7+ (only 64 bit)
+- **Python version**: Python >=3.7, <3.13 (only 64 bit)
 - **Package managers**: [pip] · [conda] (via `conda-forge`)
 
 [pip]: https://pypi.org/project/spacy/

bin/release.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+
+set -e
+
+# Insist repository is clean
+git diff-index --quiet HEAD
+
+version=$(grep "__version__ = " spacy/about.py)
+version=${version/__version__ = }
+version=${version/\'/}
+version=${version/\'/}
+version=${version/\"/}
+version=${version/\"/}
+
+echo "Pushing release-v"$version
+
+git tag -d release-v$version || true
+git push origin :release-v$version || true
+git tag release-v$version
+git push origin release-v$version

build-constraints.txt

@@ -1,6 +1,2 @@
 # build version constraints for use with wheelwright
-numpy==1.15.0; python_version=='3.7' and platform_machine!='aarch64'
-numpy==1.19.2; python_version=='3.7' and platform_machine=='aarch64'
-numpy==1.17.3; python_version=='3.8' and platform_machine!='aarch64'
-numpy==1.19.2; python_version=='3.8' and platform_machine=='aarch64'
-numpy>=1.25.0; python_version>='3.9'
+numpy>=2.0.0,<3.0.0

pyproject.toml

@@ -1,21 +1,19 @@
 [build-system]
 requires = [
     "setuptools",
-    "cython>=0.25,<3.0",
+    "cython>=3.0,<4.0",
     "cymem>=2.0.2,<2.1.0",
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
-    "thinc>=8.3.0,<8.4.0",
-    "numpy>=2.0.0,<2.1.0; python_version < '3.9'",
-    "numpy>=2.0.0,<2.1.0; python_version >= '3.9'",
+    "thinc>=8.3.4,<8.4.0",
+    "numpy>=2.0.0,<3.0.0"
 ]
 build-backend = "setuptools.build_meta"
 
 [tool.cibuildwheel]
 build = "*"
-skip = "pp* cp36* cp37* cp38* *-win32 *i686*"
+skip = "cp39* *-win32 *i686* cp3??t-* *cp310-win_arm64"
 test-skip = ""
-free-threaded-support = false
 
 archs = ["native"]
 

requirements.txt

@@ -3,28 +3,26 @@ spacy-legacy>=3.0.11,<3.1.0
 spacy-loggers>=1.0.0,<2.0.0
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
-thinc>=8.3.0,<8.4.0
+thinc>=8.3.4,<8.4.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.2.0
 srsly>=2.4.3,<3.0.0
 catalogue>=2.0.6,<2.1.0
-typer>=0.3.0,<1.0.0
-weasel>=0.1.0,<0.5.0
+typer-slim>=0.3.0,<1.0.0
+weasel>=0.4.2,<0.5.0
 # Third party dependencies
-numpy>=2.0.0; python_version < "3.9"
-numpy>=2.0.0; python_version >= "3.9"
+numpy>=2.0.0,<3.0.0
 requests>=2.13.0,<3.0.0
 tqdm>=4.38.0,<5.0.0
 pydantic>=1.7.4,!=1.8,!=1.8.1,<3.0.0
 jinja2
-langcodes>=3.2.0,<4.0.0
 # Official Python utilities
 setuptools
 packaging>=20.0
 # Development dependencies
 pre-commit>=2.13.0
-cython>=0.25,<3.0
+cython>=3.0,<4.0
 pytest>=5.2.0,!=7.1.0
 pytest-timeout>=1.3.0,<2.0.0
 mock>=2.0.0,<3.0.0
@@ -35,6 +33,6 @@ types-mock>=0.1.1
 types-setuptools>=57.0.0
 types-requests
 types-setuptools>=57.0.0
-black==22.3.0
+black>=25.0.0
 cython-lint>=0.15.0
 isort>=5.0,<6.0

setup.cfg

@@ -21,6 +21,7 @@ classifiers =
     Programming Language :: Python :: 3.10
     Programming Language :: Python :: 3.11
     Programming Language :: Python :: 3.12
+    Programming Language :: Python :: 3.13
     Topic :: Scientific/Engineering
 project_urls =
     Release notes = https://github.com/explosion/spaCy/releases
@@ -29,18 +30,18 @@ project_urls =
 [options]
 zip_safe = false
 include_package_data = true
-python_requires = >=3.9
+python_requires = >=3.9,<3.15
 # NOTE: This section is superseded by pyproject.toml and will be removed in
 # spaCy v4
 setup_requires =
-    cython>=0.25,<3.0
-    numpy>=2.0.0,<2.1.0; python_version < "3.9"
-    numpy>=2.0.0,<2.1.0; python_version >= "3.9"
+    cython>=3.0,<4.0
+    numpy>=2.0.0,<3.0.0; python_version < "3.9"
+    numpy>=2.0.0,<3.0.0; python_version >= "3.9"
     # We also need our Cython packages here to compile against
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
     murmurhash>=0.28.0,<1.1.0
-    thinc>=8.3.0,<8.4.0
+    thinc>=8.3.4,<8.4.0
 install_requires =
     # Our libraries
     spacy-legacy>=3.0.11,<3.1.0
@@ -48,13 +49,13 @@ install_requires =
     murmurhash>=0.28.0,<1.1.0
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
-    thinc>=8.3.0,<8.4.0
+    thinc>=8.3.4,<8.4.0
     wasabi>=0.9.1,<1.2.0
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
-    weasel>=0.1.0,<0.5.0
+    weasel>=0.4.2,<0.5.0
     # Third-party dependencies
-    typer>=0.3.0,<1.0.0
+    typer-slim>=0.3.0,<1.0.0
     tqdm>=4.38.0,<5.0.0
     numpy>=1.15.0; python_version < "3.9"
     numpy>=1.19.0; python_version >= "3.9"
@@ -64,7 +65,6 @@ install_requires =
     # Official Python utilities
     setuptools
     packaging>=20.0
-    langcodes>=3.2.0,<4.0.0
 
 [options.entry_points]
 console_scripts =

spacy/__init__.py

@@ -17,6 +17,7 @@ from .cli.info import info  # noqa: F401
 from .errors import Errors
 from .glossary import explain  # noqa: F401
 from .language import Language
+from .registrations import REGISTRY_POPULATED, populate_registry
 from .util import logger, registry  # noqa: F401
 from .vocab import Vocab
 

spacy/about.py

@@ -1,5 +1,5 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.8.2"
+__version__ = "3.8.11"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"

spacy/cli/_util.py

@@ -20,7 +20,7 @@ from typing import (
 import srsly
 import typer
 from click import NoSuchOption
-from click.parser import split_arg_string
+from click.shell_completion import split_arg_string
 from thinc.api import Config, ConfigValidationError, require_gpu
 from thinc.util import gpu_is_available
 from typer.main import get_command
@@ -225,13 +225,11 @@ def get_git_version(
 
 
 @overload
-def string_to_list(value: str, intify: Literal[False] = ...) -> List[str]:
-    ...
+def string_to_list(value: str, intify: Literal[False] = ...) -> List[str]: ...
 
 
 @overload
-def string_to_list(value: str, intify: Literal[True]) -> List[int]:
-    ...
+def string_to_list(value: str, intify: Literal[True]) -> List[int]: ...
 
 
 def string_to_list(value: str, intify: bool = False) -> Union[List[str], List[int]]:

spacy/cli/debug_data.py

@@ -968,16 +968,14 @@ def _compile_gold(
 
 
 @overload
-def _format_labels(labels: Iterable[str], counts: Literal[False] = False) -> str:
-    ...
+def _format_labels(labels: Iterable[str], counts: Literal[False] = False) -> str: ...
 
 
 @overload
 def _format_labels(
     labels: Iterable[Tuple[str, int]],
     counts: Literal[True],
-) -> str:
-    ...
+) -> str: ...
 
 
 def _format_labels(

spacy/cli/debug_model.py

@@ -170,7 +170,7 @@ def debug_model(
         msg.divider(f"STEP 3 - prediction")
         msg.info(str(prediction))
 
-    msg.good(f"Succesfully ended analysis - model looks good.")
+    msg.good(f"Successfully ended analysis - model looks good.")
 
 
 def _sentences():

spacy/cli/download.py

@@ -29,6 +29,7 @@ def download_cli(
     model: str = Arg(..., help="Name of pipeline package to download"),
     direct: bool = Opt(False, "--direct", "-d", "-D", help="Force direct download of name + version"),
     sdist: bool = Opt(False, "--sdist", "-S", help="Download sdist (.tar.gz) archive instead of pre-built binary wheel"),
+    url: str = Opt(None, "--url", "-U", help="Download from given url")
     # fmt: on
 ):
     """
@@ -41,13 +42,14 @@ def download_cli(
     DOCS: https://spacy.io/api/cli#download
     AVAILABLE PACKAGES: https://spacy.io/models
     """
-    download(model, direct, sdist, *ctx.args)
+    download(model, direct, sdist, url, *ctx.args)
 
 
 def download(
     model: str,
     direct: bool = False,
     sdist: bool = False,
+    custom_url: Optional[str] = None,
     *pip_args,
 ) -> None:
     if (
@@ -87,7 +89,7 @@ def download(
 
     filename = get_model_filename(model_name, version, sdist)
 
-    download_model(filename, pip_args)
+    download_model(filename, pip_args, custom_url)
     msg.good(
         "Download and installation successful",
         f"You can now load the package via spacy.load('{model_name}')",
@@ -159,12 +161,14 @@ def get_latest_version(model: str) -> str:
 
 
 def download_model(
-    filename: str, user_pip_args: Optional[Sequence[str]] = None
+    filename: str,
+    user_pip_args: Optional[Sequence[str]] = None,
+    custom_url: Optional[str] = None,
 ) -> None:
     # Construct the download URL carefully. We need to make sure we don't
     # allow relative paths or other shenanigans to trick us into download
     # from outside our own repo.
-    base_url = about.__download_url__
+    base_url = custom_url if custom_url else about.__download_url__
     # urljoin requires that the path ends with /, or the last path part will be dropped
     if not base_url.endswith("/"):
         base_url = about.__download_url__ + "/"

spacy/cli/find_threshold.py

@@ -157,9 +157,11 @@ def find_threshold(
                 exits=1,
             )
         return {
-            keys[0]: filter_config(config[keys[0]], keys[1:], full_key)
-            if len(keys) > 1
-            else config[keys[0]]
+            keys[0]: (
+                filter_config(config[keys[0]], keys[1:], full_key)
+                if len(keys) > 1
+                else config[keys[0]]
+            )
         }
 
     # Evaluate with varying threshold values.
@@ -216,12 +218,14 @@ def find_threshold(
     if len(set(scores.values())) == 1:
         wasabi.msg.warn(
             title="All scores are identical. Verify that all settings are correct.",
-            text=""
-            if (
-                not isinstance(pipe, MultiLabel_TextCategorizer)
-                or scores_key in ("cats_macro_f", "cats_micro_f")
-            )
-            else "Use `cats_macro_f` or `cats_micro_f` when optimizing the threshold for `textcat_multilabel`.",
+            text=(
+                ""
+                if (
+                    not isinstance(pipe, MultiLabel_TextCategorizer)
+                    or scores_key in ("cats_macro_f", "cats_micro_f")
+                )
+                else "Use `cats_macro_f` or `cats_micro_f` when optimizing the threshold for `textcat_multilabel`."
+            ),
         )
 
     else:

spacy/cli/init_config.py

@@ -195,9 +195,11 @@ def init_config(
         "Pipeline": ", ".join(pipeline),
         "Optimize for": optimize,
         "Hardware": variables["hardware"].upper(),
-        "Transformer": template_vars.transformer.get("name")  # type: ignore[attr-defined]
-        if template_vars.use_transformer  # type: ignore[attr-defined]
-        else None,
+        "Transformer": (
+            template_vars.transformer.get("name")  # type: ignore[attr-defined]
+            if template_vars.use_transformer  # type: ignore[attr-defined]
+            else None
+        ),
     }
     msg.info("Generated config template specific for your use case")
     for label, value in use_case.items():

spacy/compat.py

@@ -1,4 +1,5 @@
 """Helpers for Python and platform compatibility."""
+
 import sys
 
 from thinc.util import copy_array

spacy/displacy/__init__.py

@@ -4,6 +4,7 @@ spaCy's built in visualization suite for dependencies and named entities.
 DOCS: https://spacy.io/api/top-level#displacy
 USAGE: https://spacy.io/usage/visualizers
 """
+
 import warnings
 from typing import Any, Callable, Dict, Iterable, Optional, Union
 
@@ -66,7 +67,7 @@ def render(
     if jupyter or (jupyter is None and is_in_jupyter()):
         # return HTML rendered by IPython display()
         # See #4840 for details on span wrapper to disable mathjax
-        from IPython.core.display import HTML, display
+        from IPython.display import HTML, display
 
         return display(HTML('<span class="tex2jax_ignore">{}</span>'.format(html)))
     return html

spacy/lang/af/stop_words.py

@@ -1,7 +1,6 @@
 # Source: https://github.com/stopwords-iso/stopwords-af
 
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 'n
 aan
 af
@@ -53,5 +52,4 @@ vir
 was
 wat
 ʼn
-""".split()
-)
+""".split())

spacy/lang/am/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "አፕል የዩኬን ጅምር ድርጅት በ 1 ቢሊዮን ዶላር ለመግዛት አስቧል።",
     "የራስ ገዝ መኪኖች የኢንሹራንስ ኃላፊነትን ወደ አምራቾች ያዛውራሉ",

spacy/lang/am/stop_words.py

@@ -1,8 +1,7 @@
 # Stop words by Teshome Kassie http://etd.aau.edu.et/bitstream/handle/123456789/3315/Teshome%20Kassie.pdf?sequence=1&isAllowed=y
 # Stop words by Tihitina Petros http://etd.aau.edu.et/bitstream/handle/123456789/3384/Tihitina%20Petros.pdf?sequence=1&isAllowed=y
 
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 ግን አንቺ አንተ እናንተ ያንተ ያንቺ የናንተ ራስህን ራስሽን ራሳችሁን
 ሁሉ ኋላ በሰሞኑ አሉ በኋላ ሁኔታ በኩል አስታውቀዋል ሆነ በውስጥ
 አስታውሰዋል ሆኑ ባጣም እስካሁን ሆኖም በተለይ አሳሰበ ሁል በተመለከተ
@@ -29,5 +28,4 @@ STOP_WORDS = set(
 በዚህም መሆን ምንጊዜም እነዚህም በዚህና ያለ ስም
 ሲኖር ከዚህም መሆኑን በሁኔታው የማያንስ እነዚህኑ ማንም ከነዚሁ
 ያላቸውን እጅግ ሲሆኑ ለሆኑ ሊሆን  ለማናቸውም
-""".split()
-)
+""".split())

spacy/lang/ar/lex_attrs.py

@@ -1,7 +1,6 @@
 from ...attrs import LIKE_NUM
 
-_num_words = set(
-    """
+_num_words = set("""
 صفر
 واحد
 إثنان
@@ -51,11 +50,9 @@ _num_words = set(
 مليون
 مليار
 مليارات
-""".split()
-)
+""".split())
 
-_ordinal_words = set(
-    """
+_ordinal_words = set("""
 اول
 أول
 حاد
@@ -70,8 +67,7 @@ _ordinal_words = set(
 ثامن
 تاسع
 عاشر
-""".split()
-)
+""".split())
 
 
 def like_num(text):

spacy/lang/ar/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 من
 نحو
 لعل
@@ -386,5 +385,4 @@ STOP_WORDS = set(
 وإن
 ولو
 يا
-""".split()
-)
+""".split())

spacy/lang/az/examples.py

@@ -4,7 +4,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Bu bir cümlədir.",
     "Necəsən?",

spacy/lang/az/stop_words.py

@@ -1,6 +1,5 @@
 # Source: https://github.com/eliasdabbas/advertools/blob/master/advertools/stopwords.py
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 amma
 arasında
 artıq
@@ -141,5 +140,4 @@ zaman
 əlbəttə
 ən
 əslində
-""".split()
-)
+""".split())

spacy/lang/bg/stop_words.py

@@ -3,8 +3,8 @@ References:
     https://github.com/Alir3z4/stop-words - Original list, serves as a base.
     https://postvai.com/books/stop-dumi.pdf - Additions to the original list in order to improve it.
 """
-STOP_WORDS = set(
-    """
+
+STOP_WORDS = set("""
 а автентичен аз ако ала
 
 бе без беше би бивш бивша бившо бивши бил била били било благодаря близо бъдат
@@ -75,5 +75,4 @@ STOP_WORDS = set(
 юмрук
 
 я як
-""".split()
-)
+""".split())

spacy/lang/bn/examples.py

@@ -5,5 +5,4 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = ["তুই খুব ভালো", "আজ আমরা ডাক্তার দেখতে যাবো", "আমি জানি না "]

spacy/lang/bn/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 অতএব অথচ অথবা অনুযায়ী অনেক অনেকে অনেকেই অন্তত  অবধি অবশ্য অর্থাৎ অন্য অনুযায়ী অর্ধভাগে
 আগামী আগে আগেই আছে আজ আদ্যভাগে আপনার আপনি আবার আমরা আমাকে আমাদের আমার  আমি আর আরও
 ইত্যাদি ইহা
@@ -38,5 +37,4 @@ STOP_WORDS = set(
 সাধারণ সামনে সঙ্গে সঙ্গেও সব সবার সমস্ত সম্প্রতি সময় সহ সহিত সাথে সুতরাং সে  সেই সেখান সেখানে  সেটা সেটাই সেটাও সেটি স্পষ্ট স্বয়ং
 হইতে হইবে হইয়া হওয়া হওয়ায় হওয়ার হচ্ছে হত হতে হতেই হন হবে হবেন হয় হয়তো হয়নি হয়ে হয়েই হয়েছিল হয়েছে হাজার
 হয়েছেন হল হলে হলেই হলেও হলো হিসাবে হিসেবে হৈলে হোক হয় হয়ে হয়েছে হৈতে হইয়া  হয়েছিল হয়েছেন হয়নি হয়েই হয়তো হওয়া হওয়ার হওয়ায়
-""".split()
-)
+""".split())

spacy/lang/bo/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "དོན་དུ་རྒྱ་མཚོ་བླ་མ་ཞེས་བྱ་ཞིང༌།",
     "ཏཱ་ལའི་ཞེས་པ་ནི་སོག་སྐད་ཡིན་པ་དེ་བོད་སྐད་དུ་རྒྱ་མཚོའི་དོན་དུ་འཇུག",

spacy/lang/bo/stop_words.py

@@ -1,7 +1,6 @@
 # Source: https://zenodo.org/records/10148636
 
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 འི་
 །
 དུ་
@@ -194,5 +193,4 @@ STOP_WORDS = set(
 གིང་
 ཚ་
 ཀྱང
-""".split()
-)
+""".split())

spacy/lang/ca/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Apple està buscant comprar una startup del Regne Unit per mil milions de dòlars",
     "Els cotxes autònoms deleguen la responsabilitat de l'assegurança als seus fabricants",

spacy/lang/ca/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a abans ací ah així això al aleshores algun alguna algunes alguns alhora allà allí allò
 als altra altre altres amb ambdues ambdós anar ans apa aquell aquella aquelles aquells
 aquest aquesta aquestes aquests aquí
@@ -48,5 +47,4 @@ un una unes uns us últim ús
 
 va vaig vam van vas veu vosaltres vostra vostre vostres
 
-""".split()
-)
+""".split())

spacy/lang/char_classes.py

@@ -277,10 +277,10 @@ _currency = (
 # These expressions contain various unicode variations, including characters
 # used in Chinese (see #1333, #1340, #1351) – unless there are cross-language
 # conflicts, spaCy's base tokenizer should handle all of those by default
-_punct = (
-    r"… …… , : ; \! \? ¿ ؟ ¡ \( \) \[ \] \{ \} < > _ # \* & 。 ？ ！ ， 、 ； ： ～ · । ، ۔ ؛ ٪"
+_punct = r"… …… , : ; \! \? ¿ ؟ ¡ \( \) \[ \] \{ \} < > _ # \* & 。 ？ ！ ， 、 ； ： ～ · । ، ۔ ؛ ٪"
+_quotes = (
+    r'\' " ” “ ` ‘ ´ ’ ‚ , „ » « 「 」 『 』 （ ） 〔 〕 【 】 《 》 〈 〉 〈 〉  ⟦ ⟧'
 )
-_quotes = r'\' " ” “ ` ‘ ´ ’ ‚ , „ » « 「 」 『 』 （ ） 〔 〕 【 】 《 》 〈 〉 〈 〉  ⟦ ⟧'
 _hyphens = "- – — -- --- —— ~"
 
 # Various symbols like dingbats, but also emoji

spacy/lang/cs/examples.py

@@ -4,7 +4,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Máma mele maso.",
     "Příliš žluťoučký kůň úpěl ďábelské ódy.",

spacy/lang/cs/stop_words.py

@@ -1,8 +1,7 @@
 # Source: https://github.com/Alir3z4/stop-words
 # Source: https://github.com/stopwords-iso/stopwords-cs/blob/master/stopwords-cs.txt
 
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a
 aby
 ahoj
@@ -361,5 +360,4 @@ zač
 zatímco
 ze
 že
-""".split()
-)
+""".split())

spacy/lang/da/stop_words.py

@@ -1,7 +1,6 @@
 # Source: Handpicked by Jens Dahl Møllerhøj.
 
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 af aldrig alene alle allerede alligevel alt altid anden andet andre at
 
 bag begge blandt blev blive bliver burde bør
@@ -41,5 +40,4 @@ ud uden udover under undtagen
 var ved vi via vil ville vore vores vær være været
 
 øvrigt
-""".split()
-)
+""".split())

spacy/lang/da/tokenizer_exceptions.py

@@ -2,6 +2,7 @@
 Tokenizer Exceptions.
 Source: https://forkortelse.dk/ and various others.
 """
+
 from ...symbols import NORM, ORTH
 from ...util import update_exc
 from ..tokenizer_exceptions import BASE_EXCEPTIONS

spacy/lang/de/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Die ganze Stadt ist ein Startup: Shenzhen ist das Silicon Valley für Hardware-Firmen",
     "Wie deutsche Startups die Technologie vorantreiben wollen: Künstliche Intelligenz",

spacy/lang/de/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 á a ab aber ach acht achte achten achter achtes ag alle allein allem allen
 aller allerdings alles allgemeinen als also am an andere anderen anderem andern
 anders auch auf aus ausser außer ausserdem außerdem
@@ -74,5 +73,4 @@ wollt wollte wollten worden wurde würde wurden würden
 
 zehn zehnte zehnten zehnter zehntes zeit zu zuerst zugleich zum zunächst zur
 zurück zusammen zwanzig zwar zwei zweite zweiten zweiter zweites zwischen
-""".split()
-)
+""".split())

spacy/lang/dsb/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Z tym stwori so wuměnjenje a zakład za dalše wobdźěłanje přez analyzu tekstoweje struktury a semantisku anotaciju a z tym tež za tu předstajenu digitalnu online-wersiju.",
     "Mi so tu jara derje spodoba.",

spacy/lang/dsb/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a abo aby ako ale až
 
 daniž dokulaž
@@ -11,5 +10,4 @@ jolic
 pak pótom
 
 teke togodla
-""".split()
-)
+""".split())

spacy/lang/el/stop_words.py

@@ -1,7 +1,6 @@
 # Stop words
 # Link to greek stop words: https://www.translatum.gr/forum/index.php?topic=3550.0?topic=3550.0
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 αδιάκοπα αι ακόμα ακόμη ακριβώς άλλα αλλά αλλαχού άλλες άλλη άλλην
 άλλης αλλιώς αλλιώτικα άλλο άλλοι αλλοιώς αλλοιώτικα άλλον άλλος άλλοτε αλλού
 άλλους άλλων άμα άμεσα αμέσως αν ανά ανάμεσα αναμεταξύ άνευ αντί αντίπερα αντίς
@@ -83,5 +82,4 @@ STOP_WORDS = set(
 χωρίς χωριστά
 
 ω ως ωσάν ωσότου ώσπου ώστε ωστόσο ωχ
-""".split()
-)
+""".split())

spacy/lang/en/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Apple is looking at buying U.K. startup for $1 billion",
     "Autonomous cars shift insurance liability toward manufacturers",

spacy/lang/en/stop_words.py

@@ -1,6 +1,5 @@
 # Stop words
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a about above across after afterwards again against all almost alone along
 already also although always am among amongst amount an and another any anyhow
 anyone anything anyway anywhere are around as at
@@ -62,8 +61,7 @@ whereafter whereas whereby wherein whereupon wherever whether which while
 whither who whoever whole whom whose why will with within without would
 
 yet you your yours yourself yourselves
-""".split()
-)
+""".split())
 
 contractions = ["n't", "'d", "'ll", "'m", "'re", "'s", "'ve"]
 STOP_WORDS.update(contractions)

spacy/lang/es/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Apple está buscando comprar una startup del Reino Unido por mil millones de dólares.",
     "Los coches autónomos delegan la responsabilidad del seguro en sus fabricantes.",

spacy/lang/es/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a acuerdo adelante ademas además afirmó agregó ahi ahora ahí al algo alguna
 algunas alguno algunos algún alli allí alrededor ambos ante anterior antes
 apenas aproximadamente aquel aquella aquellas aquello aquellos aqui aquél
@@ -76,5 +75,4 @@ va vais vamos van varias varios vaya veces ver verdad verdadera verdadero vez
 vosotras vosotros voy vuestra vuestras vuestro vuestros
 
 y ya yo
-""".split()
-)
+""".split())

spacy/lang/et/stop_words.py

@@ -1,7 +1,6 @@
 # Source: https://github.com/stopwords-iso/stopwords-et
 
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 aga
 ei
 et
@@ -37,5 +36,4 @@ siis
 ta
 te
 ära
-""".split()
-)
+""".split())

spacy/lang/eu/stop_words.py

@@ -1,8 +1,7 @@
 # Source: https://github.com/stopwords-iso/stopwords-eu
 # https://www.ranks.nl/stopwords/basque
 # https://www.mustgo.com/worldlanguages/basque/
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 al
 anitz
 arabera
@@ -101,5 +100,4 @@ zu
 zuek
 zuen
 zuten
-""".split()
-)
+""".split())

spacy/lang/fa/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "این یک جمله نمونه می باشد.",
     "قرار ما، امروز ساعت ۲:۳۰ بعدازظهر هست!",

spacy/lang/fa/lex_attrs.py

@@ -5,8 +5,7 @@ ZWNJ_O_MIM = "‌ام"
 YE_NUN = "ین"
 
 
-_num_words = set(
-    """
+_num_words = set("""
 صفر
 یک
 دو
@@ -63,15 +62,12 @@ _num_words = set(
 کوادریلیون
 کادریلیارد
 کوینتیلیون
-""".split()
-)
+""".split())
 
-_ordinal_words = set(
-    """
+_ordinal_words = set("""
 اول
 سوم
-سی‌ام""".split()
-)
+سی‌ام""".split())
 
 _ordinal_words.update({num + MIM for num in _num_words})
 _ordinal_words.update({num + ZWNJ_O_MIM for num in _num_words})

spacy/lang/fa/stop_words.py

@@ -1,6 +1,5 @@
 # Stop words from HAZM package
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 و
 در
 به
@@ -389,5 +388,4 @@ STOP_WORDS = set(
 لذا
 زاده
 گردد
-اینجا""".split()
-)
+اینجا""".split())

spacy/lang/fi/stop_words.py

@@ -1,7 +1,6 @@
 # Source https://github.com/stopwords-iso/stopwords-fi/blob/master/stopwords-fi.txt
 # Reformatted with some minor corrections
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 aiemmin aika aikaa aikaan aikaisemmin aikaisin aikana aikoina aikoo aikovat
 aina ainakaan ainakin ainoa ainoat aiomme aion aiotte aivan ajan alas alemmas
 alkuisin alkuun alla alle aloitamme aloitan aloitat aloitatte aloitattivat
@@ -106,5 +105,4 @@ yhtäällä yhtäältä yhtään yhä yksi yksin yksittäin yleensä ylemmäs yl
 ympäri
 
 älköön älä
-""".split()
-)
+""".split())

spacy/lang/fi/tokenizer_exceptions.py

@@ -100,9 +100,9 @@ conj_contraction_negations = [
     ("eivat", "eivät"),
     ("eivät", "eivät"),
 ]
-for (base_lower, base_norm) in conj_contraction_bases:
+for base_lower, base_norm in conj_contraction_bases:
     for base in [base_lower, base_lower.title()]:
-        for (suffix, suffix_norm) in conj_contraction_negations:
+        for suffix, suffix_norm in conj_contraction_negations:
             _exc[base + suffix] = [
                 {ORTH: base, NORM: base_norm},
                 {ORTH: suffix, NORM: suffix_norm},

spacy/lang/fr/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Apple cherche à acheter une start-up anglaise pour 1 milliard de dollars",
     "Les voitures autonomes déplacent la responsabilité de l'assurance vers les constructeurs",

spacy/lang/fr/lex_attrs.py

@@ -1,24 +1,20 @@
 from ...attrs import LIKE_NUM
 
-_num_words = set(
-    """
+_num_words = set("""
 zero un une deux trois quatre cinq six sept huit neuf dix
 onze douze treize quatorze quinze seize dix-sept dix-huit dix-neuf
 vingt trente quarante cinquante soixante soixante-dix septante quatre-vingt huitante quatre-vingt-dix nonante
 cent mille mil million milliard billion quadrillion quintillion
 sextillion septillion octillion nonillion decillion
-""".split()
-)
+""".split())
 
-_ordinal_words = set(
-    """
+_ordinal_words = set("""
 premier première deuxième second seconde troisième quatrième cinquième sixième septième huitième neuvième dixième
 onzième douzième treizième quatorzième quinzième seizième dix-septième dix-huitième dix-neuvième
 vingtième trentième quarantième cinquantième soixantième soixante-dixième septantième quatre-vingtième huitantième quatre-vingt-dixième nonantième
 centième millième millionnième milliardième billionnième quadrillionnième quintillionnième
 sextillionnième septillionnième octillionnième nonillionnième decillionnième
-""".split()
-)
+""".split())
 
 
 def like_num(text):

spacy/lang/fr/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a à â abord afin ah ai aie ainsi ait allaient allons
 alors anterieur anterieure anterieures antérieur antérieure antérieures
 apres après as assez attendu au
@@ -80,5 +79,4 @@ votre votres vous vous-mêmes vu vé vôtre vôtres
 
 y
 
-""".split()
-)
+""".split())

spacy/lang/ga/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a ach ag agus an aon ar arna as
 
 ba beirt bhúr
@@ -39,5 +38,4 @@ um
 í
 
 ó ón óna ónár
-""".split()
-)
+""".split())

spacy/lang/gd/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 'ad
 'ar
 'd # iad
@@ -382,7 +381,4 @@ urrainn
 ì
 ò
 ó
-""".split(
-        "\n"
-    )
-)
+""".split("\n"))

spacy/lang/gd/tokenizer_exceptions.py

@@ -1974,9 +1974,7 @@ Tron an
 tuilleadh 's a chòir
 Tuilleadh 's a chòir
 tuilleadh sa chòir
-Tuilleadh sa chòir""".split(
-    "\n"
-):
+Tuilleadh sa chòir""".split("\n"):
     _exc[orth] = [{ORTH: orth}]
 
 

spacy/lang/grc/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "ἐρᾷ μὲν ἁγνὸς οὐρανὸς τρῶσαι χθόνα, ἔρως δὲ γαῖαν λαμβάνει γάμου τυχεῖν·",
     "εὐδαίμων Χαρίτων καὶ Μελάνιππος ἔφυ, θείας ἁγητῆρες ἐφαμερίοις φιλότατος.",

spacy/lang/grc/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 αὐτῷ αὐτοῦ αὐτῆς αὐτόν αὐτὸν αὐτῶν αὐτὸς αὐτὸ αὐτό αὐτός αὐτὴν αὐτοῖς αὐτοὺς αὔτ' αὐτὰ αὐτῇ αὐτὴ
 αὐτὼ αὑταὶ καὐτὸς αὐτά αὑτός αὐτοῖσι αὐτοῖσιν αὑτὸς αὐτήν αὐτοῖσί αὐτοί αὐτοὶ αὐτοῖο αὐτάων αὐτὰς
 αὐτέων αὐτώ αὐτάς αὐτούς αὐτή αὐταί αὐταὶ αὐτῇσιν τὠυτῷ τὠυτὸ ταὐτὰ ταύτῃ αὐτῇσι αὐτῇς αὐταῖς αὐτᾶς αὐτὰν ταὐτὸν
@@ -57,5 +56,4 @@ STOP_WORDS = set(
 
  ὣς ὡς ὥς ὧς ὥστ' ὥστε ὥσθ' ὤ ὢ 
  
- """.split()
-)
+ """.split())

spacy/lang/gu/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "લોકશાહી એ સરકારનું એક એવું તંત્ર છે જ્યાં નાગરિકો મત દ્વારા સત્તાનો ઉપયોગ કરે છે.",
     "તે ગુજરાત રાજ્યના ધરમપુર શહેરમાં આવેલું હતું",

spacy/lang/gu/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 એમ
 આ
 એ
@@ -84,5 +83,4 @@ STOP_WORDS = set(
 દર
 એટલો
 પરંતુ
-""".split()
-)
+""".split())

spacy/lang/he/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "סין מקימה קרן של 440 מיליון דולר להשקעה בהייטק בישראל",
     'רה"מ הודיע כי יחרים טקס בחסותו',

spacy/lang/he/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 אני
 את
 אתה
@@ -218,5 +217,4 @@ STOP_WORDS = set(
 אחרות
 אשר
 או
-""".split()
-)
+""".split())

spacy/lang/hi/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "एप्पल 1 अरब डॉलर के लिए यू.के. स्टार्टअप खरीदने पर विचार कर रहा है।",
     "स्वायत्त कारें निर्माताओं की ओर बीमा दायित्व रखतीं हैं।",

spacy/lang/hi/stop_words.py

@@ -1,7 +1,6 @@
 # Source: https://github.com/taranjeet/hindi-tokenizer/blob/master/stopwords.txt, https://data.mendeley.com/datasets/bsr3frvvjc/1#file-a21d5092-99d7-45d8-b044-3ae9edd391c6
 
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 अंदर
 अत
 अदि
@@ -235,5 +234,4 @@ STOP_WORDS = set(
 होते
 होना
 होने
-""".split()
-)
+""".split())

spacy/lang/hr/stop_words.py

@@ -1,6 +1,5 @@
 # Source: https://github.com/stopwords-iso/stopwords-hr
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a
 ah
 aha
@@ -340,5 +339,4 @@ zbog
 željeo
 zimus
 zum
-""".split()
-)
+""".split())

spacy/lang/hsb/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "To běšo wjelgin raźone a jo se wót luźi derje pśiwzeło. Tak som dožywiła wjelgin",
     "Jogo pśewóźowarce stej groniłej, až how w serbskich stronach njama Santa Claus nic pytaś.",

spacy/lang/hsb/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a abo ale ani
 
 dokelž
@@ -15,5 +14,4 @@ pak potom
 tež tohodla
 
 zo zoby
-""".split()
-)
+""".split())

spacy/lang/ht/__init__.py

@@ -0,0 +1,55 @@
+from typing import Callable, Optional
+
+from thinc.api import Model
+
+from ...language import BaseDefaults, Language
+from .lemmatizer import HaitianCreoleLemmatizer
+from .lex_attrs import LEX_ATTRS
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
+from .stop_words import STOP_WORDS
+from .syntax_iterators import SYNTAX_ITERATORS
+from .tag_map import TAG_MAP
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+
+
+class HaitianCreoleDefaults(BaseDefaults):
+    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    prefixes = TOKENIZER_PREFIXES
+    infixes = TOKENIZER_INFIXES
+    suffixes = TOKENIZER_SUFFIXES
+    lex_attr_getters = LEX_ATTRS
+    syntax_iterators = SYNTAX_ITERATORS
+    stop_words = STOP_WORDS
+    tag_map = TAG_MAP
+
+
+class HaitianCreole(Language):
+    lang = "ht"
+    Defaults = HaitianCreoleDefaults
+
+
+@HaitianCreole.factory(
+    "lemmatizer",
+    assigns=["token.lemma"],
+    default_config={
+        "model": None,
+        "mode": "rule",
+        "overwrite": False,
+        "scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"},
+    },
+    default_score_weights={"lemma_acc": 1.0},
+)
+def make_lemmatizer(
+    nlp: Language,
+    model: Optional[Model],
+    name: str,
+    mode: str,
+    overwrite: bool,
+    scorer: Optional[Callable],
+):
+    return HaitianCreoleLemmatizer(
+        nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
+    )
+
+
+__all__ = ["HaitianCreole"]

spacy/lang/ht/examples.py

@@ -0,0 +1,17 @@
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.ht.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+sentences = [
+    "Apple ap panse achte yon demaraj nan Wayòm Ini pou $1 milya dola",
+    "Machin otonòm fè responsablite asirans lan ale sou men fabrikan yo",
+    "San Francisco ap konsidere entèdi robo ki livre sou twotwa yo",
+    "Lond se yon gwo vil nan Wayòm Ini",
+    "Kote ou ye?",
+    "Kilès ki prezidan Lafrans?",
+    "Ki kapital Etazini?",
+    "Kile Barack Obama te fèt?",
+]

spacy/lang/ht/lemmatizer.py

@@ -0,0 +1,51 @@
+from typing import List, Tuple
+
+from ...lookups import Lookups
+from ...pipeline import Lemmatizer
+from ...tokens import Token
+
+
+class HaitianCreoleLemmatizer(Lemmatizer):
+    """
+    Minimal Haitian Creole lemmatizer.
+    Returns a word's base form based on rules and lookup,
+    or defaults to the original form.
+    """
+
+    def is_base_form(self, token: Token) -> bool:
+        morph = token.morph.to_dict()
+        upos = token.pos_.lower()
+
+        # Consider unmarked forms to be base
+        if upos in {"noun", "verb", "adj", "adv"}:
+            if not morph:
+                return True
+            if upos == "noun" and morph.get("Number") == "Sing":
+                return True
+            if upos == "verb" and morph.get("VerbForm") == "Inf":
+                return True
+            if upos == "adj" and morph.get("Degree") == "Pos":
+                return True
+        return False
+
+    def rule_lemmatize(self, token: Token) -> List[str]:
+        string = token.text.lower()
+        pos = token.pos_.lower()
+        cache_key = (token.orth, token.pos)
+        if cache_key in self.cache:
+            return self.cache[cache_key]
+
+        forms = []
+
+        # fallback rule: just return lowercased form
+        forms.append(string)
+
+        self.cache[cache_key] = forms
+        return forms
+
+    @classmethod
+    def get_lookups_config(cls, mode: str) -> Tuple[List[str], List[str]]:
+        if mode == "rule":
+            required = ["lemma_lookup", "lemma_rules", "lemma_exc", "lemma_index"]
+            return (required, [])
+        return super().get_lookups_config(mode)

spacy/lang/ht/lex_attrs.py

@@ -0,0 +1,77 @@
+from ...attrs import LIKE_NUM, NORM
+
+# Cardinal numbers in Creole
+_num_words = set("""
+zewo youn en de twa kat senk sis sèt uit nèf dis
+onz douz trèz katoz kenz sèz disèt dizwit diznèf
+vent trant karant sinkant swasant swasann-dis
+san mil milyon milya
+""".split())
+
+# Ordinal numbers in Creole (some are French-influenced, some simplified)
+_ordinal_words = set("""
+premye dezyèm twazyèm katryèm senkyèm sizyèm sètvyèm uitvyèm nèvyèm dizyèm
+onzèm douzyèm trèzyèm katozyèm kenzèm sèzyèm disetyèm dizwityèm diznèvyèm
+ventyèm trantyèm karantyèm sinkantyèm swasantyèm
+swasann-disyèm santyèm milyèm milyonnyèm milyadyèm
+""".split())
+
+NORM_MAP = {
+    "'m": "mwen",
+    "'w": "ou",
+    "'l": "li",
+    "'n": "nou",
+    "'y": "yo",
+    "’m": "mwen",
+    "’w": "ou",
+    "’l": "li",
+    "’n": "nou",
+    "’y": "yo",
+    "m": "mwen",
+    "n": "nou",
+    "l": "li",
+    "y": "yo",
+    "w": "ou",
+    "t": "te",
+    "k": "ki",
+    "p": "pa",
+    "M": "Mwen",
+    "N": "Nou",
+    "L": "Li",
+    "Y": "Yo",
+    "W": "Ou",
+    "T": "Te",
+    "K": "Ki",
+    "P": "Pa",
+}
+
+
+def like_num(text):
+    text = text.strip().lower()
+    if text.startswith(("+", "-", "±", "~")):
+        text = text[1:]
+    text = text.replace(",", "").replace(".", "")
+    if text.isdigit():
+        return True
+    if text.count("/") == 1:
+        num, denom = text.split("/")
+        if num.isdigit() and denom.isdigit():
+            return True
+    if text in _num_words:
+        return True
+    if text in _ordinal_words:
+        return True
+    # Handle things like "3yèm", "10yèm", "25yèm", etc.
+    if text.endswith("yèm") and text[:-3].isdigit():
+        return True
+    return False
+
+
+def norm_custom(text):
+    return NORM_MAP.get(text, text.lower())
+
+
+LEX_ATTRS = {
+    LIKE_NUM: like_num,
+    NORM: norm_custom,
+}

spacy/lang/ht/punctuation.py

@@ -0,0 +1,58 @@
+from ..char_classes import (
+    ALPHA,
+    ALPHA_LOWER,
+    ALPHA_UPPER,
+    CONCAT_QUOTES,
+    HYPHENS,
+    LIST_ELLIPSES,
+    LIST_ICONS,
+    LIST_PUNCT,
+    LIST_QUOTES,
+    merge_chars,
+)
+
+ELISION = "'’".replace(" ", "")
+
+_prefixes_elision = "m n l y t k w"
+_prefixes_elision += " " + _prefixes_elision.upper()
+
+TOKENIZER_PREFIXES = (
+    LIST_PUNCT
+    + LIST_QUOTES
+    + [
+        r"(?:({pe})[{el}])(?=[{a}])".format(
+            a=ALPHA, el=ELISION, pe=merge_chars(_prefixes_elision)
+        )
+    ]
+)
+
+TOKENIZER_SUFFIXES = (
+    LIST_PUNCT
+    + LIST_QUOTES
+    + LIST_ELLIPSES
+    + [
+        r"(?<=[0-9])%",  # numbers like 10%
+        r"(?<=[0-9])(?:{h})".format(h=HYPHENS),  # hyphens after numbers
+        r"(?<=[{a}])['’]".format(a=ALPHA),  # apostrophes after letters
+        r"(?<=[{a}])['’][mwlnytk](?=\s|$)".format(a=ALPHA),  # contractions
+        r"(?<=[{a}0-9])\)",  # right parenthesis after letter/number
+        r"(?<=[{a}])\.(?=\s|$)".format(
+            a=ALPHA
+        ),  # period after letter if space or end of string
+        r"(?<=\))[\.\?!]",  # punctuation immediately after right parenthesis
+    ]
+)
+
+TOKENIZER_INFIXES = (
+    LIST_ELLIPSES
+    + LIST_ICONS
+    + [
+        r"(?<=[0-9])[+\-\*^](?=[0-9-])",
+        r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
+            al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
+        ),
+        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}0-9])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
+        r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION),
+    ]
+)

spacy/lang/ht/stop_words.py

@@ -0,0 +1,47 @@
+STOP_WORDS = set("""
+a ak an ankò ant apre ap atò avan avanlè
+byen bò byenke
+
+chak
+
+de depi deja deja
+
+e en epi èske
+
+fò fòk
+
+gen genyen
+
+ki kisa kilès kote koukou konsa konbyen konn konnen kounye kouman
+
+la l laa le lè li lye lò
+
+m m' mwen
+
+nan nap nou n'
+
+ou oumenm
+
+pa paske pami pandan pito pou pral preske pwiske
+
+se selman si sou sòt
+
+ta tap tankou te toujou tou tan tout toutotan twòp tèl
+
+w w' wi wè
+
+y y' yo yon yonn
+
+non o oh eh
+
+sa san si swa si
+
+men mèsi oswa osinon
+
+""".split())
+
+# Add common contractions, with and without apostrophe variants
+contractions = ["m'", "n'", "w'", "y'", "l'", "t'", "k'"]
+for apostrophe in ["'", "’", "‘"]:
+    for word in contractions:
+        STOP_WORDS.add(word.replace("'", apostrophe))

spacy/lang/ht/syntax_iterators.py

@@ -0,0 +1,74 @@
+from typing import Iterator, Tuple, Union
+
+from ...errors import Errors
+from ...symbols import NOUN, PRON, PROPN
+from ...tokens import Doc, Span
+
+
+def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Tuple[int, int, int]]:
+    """
+    Detect base noun phrases from a dependency parse for Haitian Creole.
+    Works on both Doc and Span objects.
+    """
+
+    # Core nominal dependencies common in Haitian Creole
+    labels = [
+        "nsubj",
+        "obj",
+        "obl",
+        "nmod",
+        "appos",
+        "ROOT",
+    ]
+
+    # Modifiers to optionally include in chunk (to the right)
+    post_modifiers = ["compound", "flat", "flat:name", "fixed"]
+
+    doc = doclike.doc
+    if not doc.has_annotation("DEP"):
+        raise ValueError(Errors.E029)
+
+    np_deps = {doc.vocab.strings.add(label) for label in labels}
+    np_mods = {doc.vocab.strings.add(mod) for mod in post_modifiers}
+    conj_label = doc.vocab.strings.add("conj")
+    np_label = doc.vocab.strings.add("NP")
+    adp_pos = doc.vocab.strings.add("ADP")
+    cc_pos = doc.vocab.strings.add("CCONJ")
+
+    prev_end = -1
+    for i, word in enumerate(doclike):
+        if word.pos not in (NOUN, PROPN, PRON):
+            continue
+        if word.left_edge.i <= prev_end:
+            continue
+
+        if word.dep in np_deps:
+            right_end = word
+            # expand to include known modifiers to the right
+            for child in word.rights:
+                if child.dep in np_mods:
+                    right_end = child.right_edge
+                elif child.pos == NOUN:
+                    right_end = child.right_edge
+
+            left_index = word.left_edge.i
+            # Skip prepositions at the start
+            if word.left_edge.pos == adp_pos:
+                left_index += 1
+
+            prev_end = right_end.i
+            yield left_index, right_end.i + 1, np_label
+
+        elif word.dep == conj_label:
+            head = word.head
+            while head.dep == conj_label and head.head.i < head.i:
+                head = head.head
+            if head.dep in np_deps:
+                left_index = word.left_edge.i
+                if word.left_edge.pos == cc_pos:
+                    left_index += 1
+                prev_end = word.i
+                yield left_index, word.i + 1, np_label
+
+
+SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}

spacy/lang/ht/tag_map.py

@@ -0,0 +1,39 @@
+from spacy.symbols import (
+    ADJ,
+    ADP,
+    ADV,
+    AUX,
+    CCONJ,
+    DET,
+    INTJ,
+    NOUN,
+    NUM,
+    PART,
+    PRON,
+    PROPN,
+    PUNCT,
+    SCONJ,
+    SYM,
+    VERB,
+    X,
+)
+
+TAG_MAP = {
+    "NOUN": {"pos": NOUN},
+    "VERB": {"pos": VERB},
+    "AUX": {"pos": AUX},
+    "ADJ": {"pos": ADJ},
+    "ADV": {"pos": ADV},
+    "PRON": {"pos": PRON},
+    "DET": {"pos": DET},
+    "ADP": {"pos": ADP},
+    "SCONJ": {"pos": SCONJ},
+    "CCONJ": {"pos": CCONJ},
+    "PART": {"pos": PART},
+    "INTJ": {"pos": INTJ},
+    "NUM": {"pos": NUM},
+    "PROPN": {"pos": PROPN},
+    "PUNCT": {"pos": PUNCT},
+    "SYM": {"pos": SYM},
+    "X": {"pos": X},
+}

spacy/lang/ht/tokenizer_exceptions.py

@@ -0,0 +1,126 @@
+from spacy.symbols import NORM, ORTH
+
+
+def make_variants(base, first_norm, second_orth, second_norm):
+    return {
+        base: [
+            {ORTH: base.split("'")[0] + "'", NORM: first_norm},
+            {ORTH: second_orth, NORM: second_norm},
+        ],
+        base.capitalize(): [
+            {
+                ORTH: base.split("'")[0].capitalize() + "'",
+                NORM: first_norm.capitalize(),
+            },
+            {ORTH: second_orth, NORM: second_norm},
+        ],
+    }
+
+
+TOKENIZER_EXCEPTIONS = {"Dr.": [{ORTH: "Dr."}]}
+
+# Apostrophe forms
+TOKENIZER_EXCEPTIONS.update(make_variants("m'ap", "mwen", "ap", "ap"))
+TOKENIZER_EXCEPTIONS.update(make_variants("n'ap", "nou", "ap", "ap"))
+TOKENIZER_EXCEPTIONS.update(make_variants("l'ap", "li", "ap", "ap"))
+TOKENIZER_EXCEPTIONS.update(make_variants("y'ap", "yo", "ap", "ap"))
+TOKENIZER_EXCEPTIONS.update(make_variants("m'te", "mwen", "te", "te"))
+TOKENIZER_EXCEPTIONS.update(make_variants("m'pral", "mwen", "pral", "pral"))
+TOKENIZER_EXCEPTIONS.update(make_variants("w'ap", "ou", "ap", "ap"))
+TOKENIZER_EXCEPTIONS.update(make_variants("k'ap", "ki", "ap", "ap"))
+TOKENIZER_EXCEPTIONS.update(make_variants("p'ap", "pa", "ap", "ap"))
+TOKENIZER_EXCEPTIONS.update(make_variants("t'ap", "te", "ap", "ap"))
+
+# Non-apostrophe contractions (with capitalized variants)
+TOKENIZER_EXCEPTIONS.update(
+    {
+        "map": [
+            {ORTH: "m", NORM: "mwen"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "Map": [
+            {ORTH: "M", NORM: "Mwen"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "lem": [
+            {ORTH: "le", NORM: "le"},
+            {ORTH: "m", NORM: "mwen"},
+        ],
+        "Lem": [
+            {ORTH: "Le", NORM: "Le"},
+            {ORTH: "m", NORM: "mwen"},
+        ],
+        "lew": [
+            {ORTH: "le", NORM: "le"},
+            {ORTH: "w", NORM: "ou"},
+        ],
+        "Lew": [
+            {ORTH: "Le", NORM: "Le"},
+            {ORTH: "w", NORM: "ou"},
+        ],
+        "nap": [
+            {ORTH: "n", NORM: "nou"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "Nap": [
+            {ORTH: "N", NORM: "Nou"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "lap": [
+            {ORTH: "l", NORM: "li"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "Lap": [
+            {ORTH: "L", NORM: "Li"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "yap": [
+            {ORTH: "y", NORM: "yo"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "Yap": [
+            {ORTH: "Y", NORM: "Yo"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "mte": [
+            {ORTH: "m", NORM: "mwen"},
+            {ORTH: "te", NORM: "te"},
+        ],
+        "Mte": [
+            {ORTH: "M", NORM: "Mwen"},
+            {ORTH: "te", NORM: "te"},
+        ],
+        "mpral": [
+            {ORTH: "m", NORM: "mwen"},
+            {ORTH: "pral", NORM: "pral"},
+        ],
+        "Mpral": [
+            {ORTH: "M", NORM: "Mwen"},
+            {ORTH: "pral", NORM: "pral"},
+        ],
+        "wap": [
+            {ORTH: "w", NORM: "ou"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "Wap": [
+            {ORTH: "W", NORM: "Ou"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "kap": [
+            {ORTH: "k", NORM: "ki"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "Kap": [
+            {ORTH: "K", NORM: "Ki"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "tap": [
+            {ORTH: "t", NORM: "te"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+        "Tap": [
+            {ORTH: "T", NORM: "Te"},
+            {ORTH: "ap", NORM: "ap"},
+        ],
+    }
+)

spacy/lang/hu/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Az Apple egy brit startup vásárlását tervezi 1 milliárd dollár értékben.",
     "San Francisco vezetése mérlegeli a járdát használó szállító robotok betiltását.",

spacy/lang/hu/punctuation.py

@@ -11,7 +11,7 @@ from ..char_classes import (
 )
 
 # removing ° from the special icons to keep e.g. 99° as one token
-_concat_icons = CONCAT_ICONS.replace("\u00B0", "")
+_concat_icons = CONCAT_ICONS.replace("\u00b0", "")
 
 _currency = r"\$¢£€¥฿"
 _quotes = CONCAT_QUOTES.replace("'", "")

spacy/lang/hu/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a abban ahhoz ahogy ahol aki akik akkor akár alatt amely amelyek amelyekben
 amelyeket amelyet amelynek ami amikor amit amolyan amíg annak arra arról az
 azok azon azonban azt aztán azután azzal azért
@@ -58,5 +57,4 @@ volna volt voltak voltam voltunk
 úgy új újabb újra
 
 ő őket
-""".split()
-)
+""".split())

spacy/lang/hy/examples.py

@@ -4,7 +4,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Լոնդոնը Միացյալ Թագավորության մեծ քաղաք է։",
     "Ո՞վ է Ֆրանսիայի նախագահը։",

spacy/lang/hy/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 նա
 ողջը
 այստեղ
@@ -103,5 +102,4 @@ STOP_WORDS = set(
 այս
 մեջ
 թ
-""".split()
-)
+""".split())

spacy/lang/id/_tokenizer_exceptions_list.py

@@ -1,5 +1,4 @@
-ID_BASE_EXCEPTIONS = set(
-    """
+ID_BASE_EXCEPTIONS = set("""
 aba-aba
 abah-abah
 abal-abal
@@ -3898,5 +3897,4 @@ yel-yel
 yo-yo
 zam-zam
 zig-zag
-""".split()
-)
+""".split())

spacy/lang/id/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Indonesia merupakan negara kepulauan yang kaya akan budaya.",
     "Berapa banyak warga yang dibutuhkan saat kerja bakti?",

spacy/lang/id/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 ada adalah adanya adapun agak agaknya agar akan akankah akhir akhiri akhirnya
 aku akulah amat amatlah anda andalah antar antara antaranya apa apaan apabila
 apakah apalagi apatah artinya asal asalkan atas atau ataukah ataupun awal
@@ -114,5 +113,4 @@ ucap ucapnya ujar ujarnya umum umumnya ungkap ungkapnya untuk usah usai
 waduh wah wahai waktu waktunya walau walaupun wong
 
 yaitu yakin yakni yang
-""".split()
-)
+""".split())

spacy/lang/is/stop_words.py

@@ -1,7 +1,6 @@
 # Source: https://github.com/Xangis/extra-stopwords
 
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 afhverju
 aftan
 aftur
@@ -154,5 +153,4 @@ ykkar
 því
 þær
 ætti
-""".split()
-)
+""".split())

spacy/lang/it/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "Apple vuole comprare una startup del Regno Unito per un miliardo di dollari",
     "Le automobili a guida autonoma spostano la responsabilità assicurativa verso i produttori",

spacy/lang/it/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 a abbastanza abbia abbiamo abbiano abbiate accidenti ad adesso affinche agl
 agli ahime ahimè ai al alcuna alcuni alcuno all alla alle allo allora altri
 altrimenti altro altrove altrui anche ancora anni anno ansa anticipo assai
@@ -79,5 +78,4 @@ uguali ulteriore ultimo un un' una uno uomo
 
 v' va vale vari varia varie vario verso vi via vicino visto vita voi volta volte
 vostra vostre vostri vostro
-""".split()
-)
+""".split())

spacy/lang/ja/__init__.py

@@ -32,7 +32,6 @@ split_mode = null
 """
 
 
-@registry.tokenizers("spacy.ja.JapaneseTokenizer")
 def create_tokenizer(split_mode: Optional[str] = None):
     def japanese_tokenizer_factory(nlp):
         return JapaneseTokenizer(nlp.vocab, split_mode=split_mode)
@@ -103,9 +102,9 @@ class JapaneseTokenizer(DummyTokenizer):
                 token.dictionary_form(),  # lemma
                 token.normalized_form(),
                 token.reading_form(),
-                sub_tokens_list[idx]
-                if sub_tokens_list
-                else None,  # user_data['sub_tokens']
+                (
+                    sub_tokens_list[idx] if sub_tokens_list else None
+                ),  # user_data['sub_tokens']
             )
             for idx, token in enumerate(sudachipy_tokens)
             if len(token.surface()) > 0

spacy/lang/ja/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "アップルがイギリスの新興企業を１０億ドルで購入を検討",
     "自動運転車の損害賠償責任、自動車メーカーに一定の負担を求める",

spacy/lang/ja/stop_words.py

@@ -2,8 +2,7 @@
 # filtering out everything that wasn't hiragana. ー (one) was also added.
 # Considered keeping some non-hiragana words but too many place names were
 # present.
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 あ あっ あまり あり ある あるいは あれ
 い いい いう いく いずれ いっ いつ いる いわ
 うち
@@ -44,5 +43,4 @@ STOP_WORDS = set(
 を
 ん
 一
-""".split()
-)
+""".split())

spacy/lang/ja/tag_map.py

@@ -25,7 +25,9 @@ TAG_MAP = {
     # Universal Dependencies Mapping: (Some of the entries in this mapping are updated to v2.6 in the list below)
     # http://universaldependencies.org/ja/overview/morphology.html
     # http://universaldependencies.org/ja/pos/all.html
-    "記号-一般": {POS: NOUN},  # this includes characters used to represent sounds like ドレミ
+    "記号-一般": {
+        POS: NOUN
+    },  # this includes characters used to represent sounds like ドレミ
     "記号-文字": {
         POS: NOUN
     },  # this is for Greek and Latin characters having some meanings, or used as symbols, as in math
@@ -72,7 +74,9 @@ TAG_MAP = {
     "名詞-固有名詞-地名-国": {POS: PROPN},  # country name
     "名詞-助動詞語幹": {POS: AUX},
     "名詞-数詞": {POS: NUM},  # includes Chinese numerals
-    "名詞-普通名詞-サ変可能": {POS: NOUN},  # XXX: sometimes VERB in UDv2; suru-verb noun
+    "名詞-普通名詞-サ変可能": {
+        POS: NOUN
+    },  # XXX: sometimes VERB in UDv2; suru-verb noun
     "名詞-普通名詞-サ変形状詞可能": {POS: NOUN},
     "名詞-普通名詞-一般": {POS: NOUN},
     "名詞-普通名詞-形状詞可能": {POS: NOUN},  # XXX: sometimes ADJ in UDv2

spacy/lang/kmr/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 û
 li
 bi
@@ -40,5 +39,4 @@ gelek
 hemû
 kes
 tişt
-""".split()
-)
+""".split())

spacy/lang/kn/examples.py

@@ -5,7 +5,6 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
 sentences = [
     "ಆಪಲ್ ಒಂದು ಯು.ಕೆ. ಸ್ಟಾರ್ಟ್ಅಪ್ ಅನ್ನು ೧ ಶತಕೋಟಿ ಡಾಲರ್ಗಳಿಗೆ ಖರೀದಿಸಲು ನೋಡುತ್ತಿದೆ.",
     "ಸ್ವಾಯತ್ತ ಕಾರುಗಳು ವಿಮಾ ಹೊಣೆಗಾರಿಕೆಯನ್ನು ತಯಾರಕರ ಕಡೆಗೆ ಬದಲಾಯಿಸುತ್ತವೆ.",

spacy/lang/kn/stop_words.py

@@ -1,5 +1,4 @@
-STOP_WORDS = set(
-    """
+STOP_WORDS = set("""
 ಹಲವು
 ಮೂಲಕ
 ಹಾಗೂ
@@ -82,5 +81,4 @@ STOP_WORDS = set(
 ಎಂದು
 ನನ್ನ
 ಮೇಲೆ
-""".split()
-)
+""".split())

spacy/lang/ko/__init__.py

@@ -20,7 +20,6 @@ DEFAULT_CONFIG = """
 """
 
 
-@registry.tokenizers("spacy.ko.KoreanTokenizer")
 def create_tokenizer():
     def korean_tokenizer_factory(nlp):
         return KoreanTokenizer(nlp.vocab)