explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 03:19:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into maintenance/v4-merge-master-20240119

Browse Source
This commit is contained in:
Daniël de Kok 2024-01-19 12:27:08 +01:00
commit 81beaea70e
178 changed files with 6166 additions and 3186 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.github/FUNDING.yml vendored Normal file
View File

@ -0,0 +1 @@
custom: [https://explosion.ai/merch, https://explosion.ai/tailored-solutions]

4
.github/workflows/tests.yml vendored
View File

@ -58,7 +58,7 @@ jobs:
fail-fast: true
matrix:
os: [ubuntu-latest, windows-latest, macos-latest]
python_version: ["3.11"]
python_version: ["3.12"]
include:
- os: macos-latest
python_version: "3.8"
@ -66,6 +66,8 @@ jobs:
python_version: "3.9"
- os: windows-latest
python_version: "3.10"
- os: macos-latest
python_version: "3.11"
runs-on: ${{ matrix.os }}

2
LICENSE
View File

@ -1,6 +1,6 @@
The MIT License (MIT)
Copyright (C) 2016-2022 ExplosionAI GmbH, 2016 spaCy GmbH, 2015 Matthew Honnibal
Copyright (C) 2016-2023 ExplosionAI GmbH, 2016 spaCy GmbH, 2015 Matthew Honnibal
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal

79
README.md
View File

@ -6,23 +6,20 @@ spaCy is a library for **advanced Natural Language Processing** in Python and
Cython. It's built on the very latest research, and was designed from day one to
be used in real products.
spaCy comes with
[pretrained pipelines](https://spacy.io/models) and
currently supports tokenization and training for **70+ languages**. It features
state-of-the-art speed and **neural network models** for tagging,
parsing, **named entity recognition**, **text classification** and more,
multi-task learning with pretrained **transformers** like BERT, as well as a
spaCy comes with [pretrained pipelines](https://spacy.io/models) and currently
supports tokenization and training for **70+ languages**. It features
state-of-the-art speed and **neural network models** for tagging, parsing,
**named entity recognition**, **text classification** and more, multi-task
learning with pretrained **transformers** like BERT, as well as a
production-ready [**training system**](https://spacy.io/usage/training) and easy
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).
open-source software, released under the
[MIT license](https://github.com/explosion/spaCy/blob/master/LICENSE).
💥 **We'd love to hear more about your experience with spaCy!**
[Fill out our survey here.](https://form.typeform.com/to/aMel9q9f)
💫 **Version 3.5 out now!**
💫 **Version 3.7 out now!**
[Check out the release notes here.](https://github.com/explosion/spaCy/releases)
[![Azure Pipelines](https://img.shields.io/azure-devops/build/explosion-ai/public/8/master.svg?logo=azure-pipelines&style=flat-square&label=build)](https://dev.azure.com/explosion-ai/public/_build?definitionId=8)
[![tests](https://github.com/explosion/spaCy/actions/workflows/tests.yml/badge.svg)](https://github.com/explosion/spaCy/actions/workflows/tests.yml)
[![Current Release Version](https://img.shields.io/github/release/explosion/spacy.svg?style=flat-square&logo=github)](https://github.com/explosion/spaCy/releases)
[![pypi Version](https://img.shields.io/pypi/v/spacy.svg?style=flat-square&logo=pypi&logoColor=white)](https://pypi.org/project/spacy/)
[![conda Version](https://img.shields.io/conda/vn/conda-forge/spacy.svg?style=flat-square&logo=conda-forge&logoColor=white)](https://anaconda.org/conda-forge/spacy)
@ -35,35 +32,42 @@ open-source software, released under the [MIT license](https://github.com/explos
## 📖 Documentation
| Documentation | |
| ----------------------------- | ---------------------------------------------------------------------- |
| ⭐️ **[spaCy 101]** | New to spaCy? Here's everything you need to know! |
| 📚 **[Usage Guides]** | How to use spaCy and its features. |
| 🚀 **[New in v3.0]** | New features, backwards incompatibilities and migration guide. |
| 🪐 **[Project Templates]** | End-to-end workflows you can clone, modify and run. |
| 🎛 **[API Reference]** | The detailed reference for spaCy's API. |
| 📦 **[Models]** | Download trained pipelines for spaCy. |
| 🌌 **[Universe]** | Plugins, extensions, demos and books from the spaCy ecosystem. |
| ⚙️ **[spaCy VS Code Extension]** | Additional tooling and features for working with spaCy's config files. |
| 👩‍🏫 **[Online Course]** | Learn spaCy in this free and interactive online course. |
| 📺 **[Videos]** | Our YouTube channel with video tutorials, talks and more. |
| 🛠 **[Changelog]** | Changes and version history. |
| 💝 **[Contribute]** | How to contribute to the spaCy project and code base. |
| <a href="https://explosion.ai/spacy-tailored-pipelines"><img src="https://user-images.githubusercontent.com/13643239/152853098-1c761611-ccb0-4ec6-9066-b234552831fe.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-pipelines)** |
| <a href="https://explosion.ai/spacy-tailored-analysis"><img src="https://user-images.githubusercontent.com/1019791/206151300-b00cd189-e503-4797-aa1e-1bb6344062c5.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-analysis)** |
| Documentation | |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| ⭐️ **[spaCy 101]** | New to spaCy? Here's everything you need to know! |
| 📚 **[Usage Guides]** | How to use spaCy and its features. |
| 🚀 **[New in v3.0]** | New features, backwards incompatibilities and migration guide. |
| 🪐 **[Project Templates]** | End-to-end workflows you can clone, modify and run. |
| 🎛 **[API Reference]** | The detailed reference for spaCy's API. |
| ⏩ **[GPU Processing]** | Use spaCy with CUDA-compatible GPU processing. |
| 📦 **[Models]** | Download trained pipelines for spaCy. |
| 🦙 **[Large Language Models]** | Integrate LLMs into spaCy pipelines. |
| 🌌 **[Universe]** | Plugins, extensions, demos and books from the spaCy ecosystem. |
| ⚙️ **[spaCy VS Code Extension]** | Additional tooling and features for working with spaCy's config files. |
| 👩‍🏫 **[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. |
| 🛠 **[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! |
| <a href="https://explosion.ai/tailored-solutions"><img src="https://github.com/explosion/spaCy/assets/13643239/36d2a42e-98c0-4599-90e1-788ef75181be" width="150" alt="Tailored Solutions"/></a> | Custom NLP consulting, implementation and strategic advice by spaCy’s core development team. Streamlined, production-ready, predictable and maintainable. Send us an email or take our 5-minute questionnaire, and well'be in touch! **[Learn more &rarr;](https://explosion.ai/tailored-solutions)** |
[spacy 101]: https://spacy.io/usage/spacy-101
[new in v3.0]: https://spacy.io/usage/v3
[usage guides]: https://spacy.io/usage/
[api reference]: https://spacy.io/api/
[gpu processing]: https://spacy.io/usage#gpu
[models]: https://spacy.io/models
[large language models]: https://spacy.io/usage/large-language-models
[universe]: https://spacy.io/universe
[spaCy VS Code Extension]: https://github.com/explosion/spacy-vscode
[spacy vs code extension]: https://github.com/explosion/spacy-vscode
[videos]: https://www.youtube.com/c/ExplosionAI
[online course]: https://course.spacy.io
[blog]: https://explosion.ai
[project templates]: https://github.com/explosion/projects
[changelog]: https://spacy.io/usage#changelog
[contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
[swag]: https://explosion.ai/merch
## 💬 Where to ask questions
@ -92,7 +96,9 @@ more people can benefit from it.
- State-of-the-art speed
- Production-ready **training system**
- Linguistically-motivated **tokenization**
- Components for named **entity recognition**, part-of-speech-tagging, dependency parsing, sentence segmentation, **text classification**, lemmatization, morphological analysis, entity linking and more
- Components for named **entity recognition**, part-of-speech-tagging,
dependency parsing, sentence segmentation, **text classification**,
lemmatization, morphological analysis, entity linking and more
- Easily extensible with **custom components** and attributes
- Support for custom models in **PyTorch**, **TensorFlow** and other frameworks
- Built in **visualizers** for syntax and NER
@ -118,8 +124,8 @@ For detailed installation instructions, see the
### pip
Using pip, spaCy releases are available as source packages and binary wheels.
Before you install spaCy and its dependencies, make sure that
your `pip`, `setuptools` and `wheel` are up to date.
Before you install spaCy and its dependencies, make sure that your `pip`,
`setuptools` and `wheel` are up to date.
```bash
pip install -U pip setuptools wheel
@ -174,9 +180,9 @@ with the new version.
## 📦 Download model packages
Trained pipelines for spaCy can be installed as **Python packages**. This
means that they're a component of your application, just like any other module.
Models can be installed using spaCy's [`download`](https://spacy.io/api/cli#download)
Trained pipelines for spaCy can be installed as **Python packages**. This means
that they're a component of your application, just like any other module. Models
can be installed using spaCy's [`download`](https://spacy.io/api/cli#download)
command, or manually by pointing pip to a path or URL.
| Documentation | |
@ -242,8 +248,7 @@ do that depends on your system.
| **Mac** | Install a recent version of [XCode](https://developer.apple.com/xcode/), including the so-called "Command Line Tools". macOS and OS X ship with Python and git preinstalled. |
| **Windows** | Install a version of the [Visual C++ Build Tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/) or [Visual Studio Express](https://visualstudio.microsoft.com/vs/express/) that matches the version that was used to compile your Python interpreter. |
For more details
and instructions, see the documentation on
For more details and instructions, see the documentation on
[compiling spaCy from source](https://spacy.io/usage#source) and the
[quickstart widget](https://spacy.io/usage#section-quickstart) to get the right
commands for your platform and Python version.

7
build-constraints.txt
View File

@ -1,7 +1,4 @@
# build version constraints for use with wheelwright + multibuild
# build version constraints for use with wheelwright
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==1.19.3; python_version=='3.9'
numpy==1.21.3; python_version=='3.10'
numpy==1.23.2; python_version=='3.11'
numpy; python_version>='3.12'
numpy>=1.25.0; python_version>='3.9'

39
extra/DEVELOPER_DOCS/Listeners.md
View File

@ -1,14 +1,17 @@
# Listeners
1. [Overview](#1-overview)
2. [Initialization](#2-initialization)
- [A. Linking listeners to the embedding component](#2a-linking-listeners-to-the-embedding-component)
- [B. Shape inference](#2b-shape-inference)
3. [Internal communication](#3-internal-communication)
- [A. During prediction](#3a-during-prediction)
- [B. During training](#3b-during-training)
- [C. Frozen components](#3c-frozen-components)
4. [Replacing listener with standalone](#4-replacing-listener-with-standalone)
- [1. Overview](#1-overview)
- [2. Initialization](#2-initialization)
- [2A. Linking listeners to the embedding component](#2a-linking-listeners-to-the-embedding-component)
- [2B. Shape inference](#2b-shape-inference)
- [3. Internal communication](#3-internal-communication)
- [3A. During prediction](#3a-during-prediction)
- [3B. During training](#3b-during-training)
- [Training with multiple listeners](#training-with-multiple-listeners)
- [3C. Frozen components](#3c-frozen-components)
- [The Tok2Vec or Transformer is frozen](#the-tok2vec-or-transformer-is-frozen)
- [The upstream component is frozen](#the-upstream-component-is-frozen)
- [4. Replacing listener with standalone](#4-replacing-listener-with-standalone)
## 1. Overview
@ -62,7 +65,7 @@ of this `find_listener()` method will specifically identify sublayers of a model
If it's a Transformer-based pipeline, a
[`transformer` component](https://github.com/explosion/spacy-transformers/blob/master/spacy_transformers/pipeline_component.py)
has a similar implementation but its `find_listener()` function will specifically look for `TransformerListener`
has a similar implementation but its `find_listener()` function will specifically look for `TransformerListener`
sublayers of downstream components.
### 2B. Shape inference
@ -154,7 +157,7 @@ as a tagger or a parser. This used to be impossible before 3.1, but has become s
embedding component in the [`annotating_components`](https://spacy.io/usage/training#annotating-components)
list of the config. This works like any other "annotating component" because it relies on the `Doc` attributes.
However, if the `Tok2Vec` or `Transformer` is frozen, and not present in `annotating_components`, and a related
However, if the `Tok2Vec` or `Transformer` is frozen, and not present in `annotating_components`, and a related
listener isn't frozen, then a `W086` warning is shown and further training of the pipeline will likely end with `E954`.
#### The upstream component is frozen
@ -216,5 +219,17 @@ new_model = tok2vec_model.attrs["replace_listener"](new_model)
```
The new config and model are then properly stored on the `nlp` object.
Note that this functionality (running the replacement for a transformer listener) was broken prior to
Note that this functionality (running the replacement for a transformer listener) was broken prior to
`spacy-transformers` 1.0.5.
In spaCy 3.7, `Language.replace_listeners` was updated to pass the following additional arguments to the `replace_listener` callback:
the listener to be replaced and the `tok2vec`/`transformer` pipe from which the new model was copied. To maintain backwards-compatiblity,
the method only passes these extra arguments for callbacks that support them:
```
def replace_listener_pre_37(copied_tok2vec_model):
...
def replace_listener_post_37(copied_tok2vec_model, replaced_listener, tok2vec_pipe):
...
```

42
licenses/3rd_party_licenses.txt
View File

@ -158,3 +158,45 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
SciPy
-----
* Files: scorer.py
The implementation of trapezoid() is adapted from SciPy, which is distributed
under the following license:
New BSD License
Copyright (c) 2001-2002 Enthought, Inc. 2003-2023, SciPy Developers.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following
disclaimer in the documentation and/or other materials provided
with the distribution.
3. Neither the name of the copyright holder nor the names of its
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

3
pyproject.toml
View File

@ -6,7 +6,8 @@ requires = [
"preshed>=3.0.2,<3.1.0",
"murmurhash>=0.28.0,<1.1.0",
"thinc>=9.0.0.dev4,<9.1.0",
"numpy>=1.15.0",
"numpy>=1.15.0; python_version < '3.9'",
"numpy>=1.25.0; python_version >= '3.9'",
]
build-backend = "setuptools.build_meta"

9
requirements.txt
View File

@ -10,13 +10,14 @@ 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,<0.10.0
pathy>=0.10.0
smart-open>=5.2.1,<7.0.0
weasel>=0.1.0,<0.4.0
# Third party dependencies
numpy>=1.15.0
numpy>=1.15.0; python_version < "3.9"
numpy>=1.19.0; python_version >= "3.9"
requests>=2.13.0,<3.0.0
tqdm>=4.38.0,<5.0.0
pydantic>=1.7.4,!=1.8,!=1.8.1,<1.11.0
pydantic>=1.7.4,!=1.8,!=1.8.1,<3.0.0
jinja2
langcodes>=3.2.0,<4.0.0
# Official Python utilities
@ -36,5 +37,5 @@ types-setuptools>=57.0.0
types-requests
types-setuptools>=57.0.0
black==22.3.0
cython-lint>=0.15.0; python_version >= "3.7"
cython-lint>=0.15.0
isort>=5.0,<6.0

18
setup.cfg
View File

@ -30,9 +30,12 @@ project_urls =
zip_safe = false
include_package_data = true
python_requires = >=3.8
# NOTE: This section is superseded by pyproject.toml and will be removed in
# spaCy v4
setup_requires =
cython>=0.25,<3.0
numpy>=1.15.0
numpy>=1.15.0; python_version < "3.9"
numpy>=1.19.0; 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
@ -49,14 +52,15 @@ install_requires =
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,<0.4.0
# Third-party dependencies
typer>=0.3.0,<0.10.0
pathy>=0.10.0
smart-open>=5.2.1,<7.0.0
tqdm>=4.38.0,<5.0.0
numpy>=1.15.0
numpy>=1.15.0; python_version < "3.9"
numpy>=1.19.0; python_version >= "3.9"
requests>=2.13.0,<3.0.0
pydantic>=1.7.4,!=1.8,!=1.8.1,<1.11.0
pydantic>=1.7.4,!=1.8,!=1.8.1,<3.0.0
jinja2
# Official Python utilities
setuptools
@ -71,9 +75,7 @@ console_scripts =
lookups =
spacy_lookups_data>=1.0.3,<1.1.0
transformers =
spacy_transformers>=1.1.2,<1.3.0
ray =
spacy_ray>=0.1.0,<1.0.0
spacy_transformers>=1.1.2,<1.4.0
cuda =
cupy>=5.0.0b4,<13.0.0
cuda80 =
@ -108,6 +110,8 @@ cuda117 =
cupy-cuda117>=5.0.0b4,<13.0.0
cuda11x =
cupy-cuda11x>=11.0.0,<13.0.0
cuda12x =
cupy-cuda12x>=11.5.0,<13.0.0
cuda-autodetect =
cupy-wheel>=11.0.0,<13.0.0
apple =

32
setup.py
View File

@ -1,10 +1,9 @@
#!/usr/bin/env python
from setuptools import Extension, setup, find_packages
import sys
import platform
import numpy
from distutils.command.build_ext import build_ext
from distutils.sysconfig import get_python_inc
from setuptools.command.build_ext import build_ext
from sysconfig import get_path
from pathlib import Path
import shutil
from Cython.Build import cythonize
@ -80,6 +79,7 @@ COMPILER_DIRECTIVES = {
"language_level": -3,
"embedsignature": True,
"annotation_typing": False,
"profile": sys.version_info < (3, 12),
}
# Files to copy into the package that are otherwise not included
COPY_FILES = {
@ -89,30 +89,6 @@ COPY_FILES = {
}
def is_new_osx():
"""Check whether we're on OSX >= 10.7"""
if sys.platform != "darwin":
return False
mac_ver = platform.mac_ver()[0]
if mac_ver.startswith("10"):
minor_version = int(mac_ver.split(".")[1])
if minor_version >= 7:
return True
else:
return False
return False
if is_new_osx():
# On Mac, use libc++ because Apple deprecated use of
# libstdc
COMPILE_OPTIONS["other"].append("-stdlib=libc++")
LINK_OPTIONS["other"].append("-lc++")
# g++ (used by unix compiler on mac) links to libstdc++ as a default lib.
# See: https://stackoverflow.com/questions/1653047/avoid-linking-to-libstdc
LINK_OPTIONS["other"].append("-nodefaultlibs")
# By subclassing build_extensions we have the actual compiler that will be used which is really known only after finalize_options
# http://stackoverflow.com/questions/724664/python-distutils-how-to-get-a-compiler-that-is-going-to-be-used
class build_ext_options:
@ -205,7 +181,7 @@ def setup_package():
include_dirs = [
numpy.get_include(),
get_python_inc(plat_specific=True),
get_path("include"),
]
ext_modules = []
ext_modules.append(

1
spacy/attrs.pyx
View File

@ -1,3 +1,4 @@
# cython: profile=False
from .errors import Errors
IOB_STRINGS = ("", "I", "O", "B")

21
spacy/cli/__init__.py
View File

@ -14,6 +14,7 @@ from .debug_diff import debug_diff # noqa: F401
from .debug_model import debug_model # noqa: F401
from .download import download # noqa: F401
from .evaluate import evaluate # noqa: F401
from .find_function import find_function # noqa: F401
from .find_threshold import find_threshold # noqa: F401
from .info import info # noqa: F401
from .init_config import fill_config, init_config # noqa: F401
@ -21,15 +22,17 @@ from .init_pipeline import init_pipeline_cli # noqa: F401
from .package import package # noqa: F401
from .pretrain import pretrain # noqa: F401
from .profile import profile # noqa: F401
from .project.assets import project_assets # noqa: F401
from .project.clone import project_clone # noqa: F401
from .project.document import project_document # noqa: F401
from .project.dvc import project_update_dvc # noqa: F401
from .project.pull import project_pull # noqa: F401
from .project.push import project_push # noqa: F401
from .project.run import project_run # noqa: F401
from .train import train_cli # noqa: F401
from .validate import validate # noqa: F401
from .project.assets import project_assets # type: ignore[attr-defined] # noqa: F401
from .project.clone import project_clone # type: ignore[attr-defined] # noqa: F401
from .project.document import ( # type: ignore[attr-defined] # noqa: F401
project_document,
)
from .project.dvc import project_update_dvc # type: ignore[attr-defined] # noqa: F401
from .project.pull import project_pull # type: ignore[attr-defined] # noqa: F401
from .project.push import project_push # type: ignore[attr-defined] # noqa: F401
from .project.run import project_run # type: ignore[attr-defined] # noqa: F401
from .train import train_cli # type: ignore[attr-defined] # noqa: F401
from .validate import validate # type: ignore[attr-defined] # noqa: F401
@app.command("link", no_args_is_help=True, deprecated=True, hidden=True)

333
spacy/cli/_util.py
View File

@ -26,10 +26,11 @@ from thinc.api import Config, ConfigValidationError, require_gpu
from thinc.util import gpu_is_available
from typer.main import get_command
from wasabi import Printer, msg
from weasel import app as project_cli
from .. import about
from ..errors import RENAMED_LANGUAGE_CODES
from ..schemas import ProjectConfigSchema, validate
from ..schemas import validate
from ..util import (
ENV_VARS,
SimpleFrozenDict,
@ -41,15 +42,10 @@ from ..util import (
run_command,
)
if TYPE_CHECKING:
from pathy import FluidPath # noqa: F401
SDIST_SUFFIX = ".tar.gz"
WHEEL_SUFFIX = "-py3-none-any.whl"
PROJECT_FILE = "project.yml"
PROJECT_LOCK = "project.lock"
COMMAND = "python -m spacy"
NAME = "spacy"
HELP = """spaCy Command-line Interface
@ -75,11 +71,10 @@ Opt = typer.Option
app = typer.Typer(name=NAME, help=HELP)
benchmark_cli = typer.Typer(name="benchmark", help=BENCHMARK_HELP, no_args_is_help=True)
project_cli = typer.Typer(name="project", help=PROJECT_HELP, no_args_is_help=True)
debug_cli = typer.Typer(name="debug", help=DEBUG_HELP, no_args_is_help=True)
init_cli = typer.Typer(name="init", help=INIT_HELP, no_args_is_help=True)
app.add_typer(project_cli)
app.add_typer(project_cli, name="project", help=PROJECT_HELP, no_args_is_help=True)
app.add_typer(debug_cli)
app.add_typer(benchmark_cli)
app.add_typer(init_cli)
@ -164,148 +159,6 @@ def _handle_renamed_language_codes(lang: Optional[str]) -> None:
)
def load_project_config(
path: Path, interpolate: bool = True, overrides: Dict[str, Any] = SimpleFrozenDict()
) -> Dict[str, Any]:
"""Load the project.yml file from a directory and validate it. Also make
sure that all directories defined in the config exist.
path (Path): The path to the project directory.
interpolate (bool): Whether to substitute project variables.
overrides (Dict[str, Any]): Optional config overrides.
RETURNS (Dict[str, Any]): The loaded project.yml.
"""
config_path = path / PROJECT_FILE
if not config_path.exists():
msg.fail(f"Can't find {PROJECT_FILE}", config_path, exits=1)
invalid_err = f"Invalid {PROJECT_FILE}. Double-check that the YAML is correct."
try:
config = srsly.read_yaml(config_path)
except ValueError as e:
msg.fail(invalid_err, e, exits=1)
errors = validate(ProjectConfigSchema, config)
if errors:
msg.fail(invalid_err)
print("\n".join(errors))
sys.exit(1)
validate_project_version(config)
validate_project_commands(config)
if interpolate:
err = f"{PROJECT_FILE} validation error"
with show_validation_error(title=err, hint_fill=False):
config = substitute_project_variables(config, overrides)
# Make sure directories defined in config exist
for subdir in config.get("directories", []):
dir_path = path / subdir
if not dir_path.exists():
dir_path.mkdir(parents=True)
return config
def substitute_project_variables(
config: Dict[str, Any],
overrides: Dict[str, Any] = SimpleFrozenDict(),
key: str = "vars",
env_key: str = "env",
) -> Dict[str, Any]:
"""Interpolate variables in the project file using the config system.
config (Dict[str, Any]): The project config.
overrides (Dict[str, Any]): Optional config overrides.
key (str): Key containing variables in project config.
env_key (str): Key containing environment variable mapping in project config.
RETURNS (Dict[str, Any]): The interpolated project config.
"""
config.setdefault(key, {})
config.setdefault(env_key, {})
# Substitute references to env vars with their values
for config_var, env_var in config[env_key].items():
config[env_key][config_var] = _parse_override(os.environ.get(env_var, ""))
# Need to put variables in the top scope again so we can have a top-level
# section "project" (otherwise, a list of commands in the top scope wouldn't)
# be allowed by Thinc's config system
cfg = Config({"project": config, key: config[key], env_key: config[env_key]})
cfg = Config().from_str(cfg.to_str(), overrides=overrides)
interpolated = cfg.interpolate()
return dict(interpolated["project"])
def validate_project_version(config: Dict[str, Any]) -> None:
"""If the project defines a compatible spaCy version range, chec that it's
compatible with the current version of spaCy.
config (Dict[str, Any]): The loaded config.
"""
spacy_version = config.get("spacy_version", None)
if spacy_version and not is_compatible_version(about.__version__, spacy_version):
err = (
f"The {PROJECT_FILE} specifies a spaCy version range ({spacy_version}) "
f"that's not compatible with the version of spaCy you're running "
f"({about.__version__}). You can edit version requirement in the "
f"{PROJECT_FILE} to load it, but the project may not run as expected."
)
msg.fail(err, exits=1)
def validate_project_commands(config: Dict[str, Any]) -> None:
"""Check that project commands and workflows are valid, don't contain
duplicates, don't clash and only refer to commands that exist.
config (Dict[str, Any]): The loaded config.
"""
command_names = [cmd["name"] for cmd in config.get("commands", [])]
workflows = config.get("workflows", {})
duplicates = set([cmd for cmd in command_names if command_names.count(cmd) > 1])
if duplicates:
err = f"Duplicate commands defined in {PROJECT_FILE}: {', '.join(duplicates)}"
msg.fail(err, exits=1)
for workflow_name, workflow_steps in workflows.items():
if workflow_name in command_names:
err = f"Can't use workflow name '{workflow_name}': name already exists as a command"
msg.fail(err, exits=1)
for step in workflow_steps:
if step not in command_names:
msg.fail(
f"Unknown command specified in workflow '{workflow_name}': {step}",
f"Workflows can only refer to commands defined in the 'commands' "
f"section of the {PROJECT_FILE}.",
exits=1,
)
def get_hash(data, exclude: Iterable[str] = tuple()) -> str:
"""Get the hash for a JSON-serializable object.
data: The data to hash.
exclude (Iterable[str]): Top-level keys to exclude if data is a dict.
RETURNS (str): The hash.
"""
if isinstance(data, dict):
data = {k: v for k, v in data.items() if k not in exclude}
data_str = srsly.json_dumps(data, sort_keys=True).encode("utf8")
return hashlib.md5(data_str).hexdigest()
def get_checksum(path: Union[Path, str]) -> str:
"""Get the checksum for a file or directory given its file path. If a
directory path is provided, this uses all files in that directory.
path (Union[Path, str]): The file or directory path.
RETURNS (str): The checksum.
"""
path = Path(path)
if not (path.is_file() or path.is_dir()):
msg.fail(f"Can't get checksum for {path}: not a file or directory", exits=1)
if path.is_file():
return hashlib.md5(Path(path).read_bytes()).hexdigest()
else:
# TODO: this is currently pretty slow
dir_checksum = hashlib.md5()
for sub_file in sorted(fp for fp in path.rglob("*") if fp.is_file()):
dir_checksum.update(sub_file.read_bytes())
return dir_checksum.hexdigest()
@contextmanager
def show_validation_error(
file_path: Optional[Union[str, Path]] = None,
@ -370,166 +223,10 @@ def import_code(code_path: Optional[Union[Path, str]]) -> None:
msg.fail(f"Couldn't load Python code: {code_path}", e, exits=1)
def upload_file(src: Path, dest: Union[str, "FluidPath"]) -> None:
"""Upload a file.
src (Path): The source path.
url (str): The destination URL to upload to.
"""
import smart_open
# Create parent directories for local paths
if isinstance(dest, Path):
if not dest.parent.exists():
dest.parent.mkdir(parents=True)
dest = str(dest)
with smart_open.open(dest, mode="wb") as output_file:
with src.open(mode="rb") as input_file:
output_file.write(input_file.read())
def download_file(
src: Union[str, "FluidPath"], dest: Path, *, force: bool = False
) -> None:
"""Download a file using smart_open.
url (str): The URL of the file.
dest (Path): The destination path.
force (bool): Whether to force download even if file exists.
If False, the download will be skipped.
"""
import smart_open
if dest.exists() and not force:
return None
src = str(src)
with smart_open.open(src, mode="rb", compression="disable") as input_file:
with dest.open(mode="wb") as output_file:
shutil.copyfileobj(input_file, output_file)
def ensure_pathy(path):
"""Temporary helper to prevent importing Pathy globally (which can cause
slow and annoying Google Cloud warning)."""
from pathy import Pathy # noqa: F811
return Pathy.fluid(path)
def git_checkout(
repo: str, subpath: str, dest: Path, *, branch: str = "master", sparse: bool = False
):
git_version = get_git_version()
if dest.exists():
msg.fail("Destination of checkout must not exist", exits=1)
if not dest.parent.exists():
msg.fail("Parent of destination of checkout must exist", exits=1)
if sparse and git_version >= (2, 22):
return git_sparse_checkout(repo, subpath, dest, branch)
elif sparse:
# Only show warnings if the user explicitly wants sparse checkout but
# the Git version doesn't support it
err_old = (
f"You're running an old version of Git (v{git_version[0]}.{git_version[1]}) "
f"that doesn't fully support sparse checkout yet."
)
err_unk = "You're running an unknown version of Git, so sparse checkout has been disabled."
msg.warn(
f"{err_unk if git_version == (0, 0) else err_old} "
f"This means that more files than necessary may be downloaded "
f"temporarily. To only download the files needed, make sure "
f"you're using Git v2.22 or above."
)
with make_tempdir() as tmp_dir:
cmd = f"git -C {tmp_dir} clone {repo} . -b {branch}"
run_command(cmd, capture=True)
# We need Path(name) to make sure we also support subdirectories
try:
source_path = tmp_dir / Path(subpath)
if not is_subpath_of(tmp_dir, source_path):
err = f"'{subpath}' is a path outside of the cloned repository."
msg.fail(err, repo, exits=1)
shutil.copytree(str(source_path), str(dest))
except FileNotFoundError:
err = f"Can't clone {subpath}. Make sure the directory exists in the repo (branch '{branch}')"
msg.fail(err, repo, exits=1)
def git_sparse_checkout(repo, subpath, dest, branch):
# We're using Git, partial clone and sparse checkout to
# only clone the files we need
# This ends up being RIDICULOUS. omg.
# So, every tutorial and SO post talks about 'sparse checkout'...But they
# go and *clone* the whole repo. Worthless. And cloning part of a repo
# turns out to be completely broken. The only way to specify a "path" is..
# a path *on the server*? The contents of which, specifies the paths. Wat.
# Obviously this is hopelessly broken and insecure, because you can query
# arbitrary paths on the server! So nobody enables this.
# What we have to do is disable *all* files. We could then just checkout
# the path, and it'd "work", but be hopelessly slow...Because it goes and
# transfers every missing object one-by-one. So the final piece is that we
# need to use some weird git internals to fetch the missings in bulk, and
# *that* we can do by path.
# We're using Git and sparse checkout to only clone the files we need
with make_tempdir() as tmp_dir:
# This is the "clone, but don't download anything" part.
cmd = (
f"git clone {repo} {tmp_dir} --no-checkout --depth 1 "
f"-b {branch} --filter=blob:none"
)
run_command(cmd)
# Now we need to find the missing filenames for the subpath we want.
# Looking for this 'rev-list' command in the git --help? Hah.
cmd = f"git -C {tmp_dir} rev-list --objects --all --missing=print -- {subpath}"
ret = run_command(cmd, capture=True)
git_repo = _http_to_git(repo)
# Now pass those missings into another bit of git internals
missings = " ".join([x[1:] for x in ret.stdout.split() if x.startswith("?")])
if not missings:
err = (
f"Could not find any relevant files for '{subpath}'. "
f"Did you specify a correct and complete path within repo '{repo}' "
f"and branch {branch}?"
)
msg.fail(err, exits=1)
cmd = f"git -C {tmp_dir} fetch-pack {git_repo} {missings}"
run_command(cmd, capture=True)
# And finally, we can checkout our subpath
cmd = f"git -C {tmp_dir} checkout {branch} {subpath}"
run_command(cmd, capture=True)
# Get a subdirectory of the cloned path, if appropriate
source_path = tmp_dir / Path(subpath)
if not is_subpath_of(tmp_dir, source_path):
err = f"'{subpath}' is a path outside of the cloned repository."
msg.fail(err, repo, exits=1)
shutil.move(str(source_path), str(dest))
def git_repo_branch_exists(repo: str, branch: str) -> bool:
"""Uses 'git ls-remote' to check if a repository and branch exists
repo (str): URL to get repo.
branch (str): Branch on repo to check.
RETURNS (bool): True if repo:branch exists.
"""
get_git_version()
cmd = f"git ls-remote {repo} {branch}"
# We might be tempted to use `--exit-code` with `git ls-remote`, but
# `run_command` handles the `returncode` for us, so we'll rely on
# the fact that stdout returns '' if the requested branch doesn't exist
ret = run_command(cmd, capture=True)
exists = ret.stdout != ""
return exists
def get_git_version(
error: str = "Could not run 'git'. Make sure it's installed and the executable is available.",
) -> Tuple[int, int]:
"""Get the version of git and raise an error if calling 'git --version' fails.
error (str): The error message to show.
RETURNS (Tuple[int, int]): The version as a (major, minor) tuple. Returns
(0, 0) if the version couldn't be determined.
@ -545,30 +242,6 @@ def get_git_version(
return int(version[0]), int(version[1])
def _http_to_git(repo: str) -> str:
if repo.startswith("http://"):
repo = repo.replace(r"http://", r"https://")
if repo.startswith(r"https://"):
repo = repo.replace("https://", "git@").replace("/", ":", 1)
if repo.endswith("/"):
repo = repo[:-1]
repo = f"{repo}.git"
return repo
def is_subpath_of(parent, child):
"""
Check whether `child` is a path contained within `parent`.
"""
# Based on https://stackoverflow.com/a/37095733 .
# In Python 3.9, the `Path.is_relative_to()` method will supplant this, so
# we can stop using crusty old os.path functions.
parent_realpath = os.path.realpath(parent)
child_realpath = os.path.realpath(child)
return os.path.commonpath([parent_realpath, child_realpath]) == parent_realpath
@overload
def string_to_list(value: str, intify: Literal[False] = ...) -> List[str]:
...

4
spacy/cli/apply.py
View File

@ -133,7 +133,9 @@ def apply(
if len(text_files) > 0:
streams.append(_stream_texts(text_files))
datagen = cast(DocOrStrStream, chain(*streams))
for doc in tqdm.tqdm(nlp.pipe(datagen, batch_size=batch_size, n_process=n_process)):
for doc in tqdm.tqdm(
nlp.pipe(datagen, batch_size=batch_size, n_process=n_process), disable=None
):
docbin.add(doc)
if output_file.suffix == "":
output_file = output_file.with_suffix(".spacy")

3
spacy/cli/assemble.py
View File

@ -40,7 +40,8 @@ def assemble_cli(
DOCS: https://spacy.io/api/cli#assemble
"""
util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
if verbose:
util.logger.setLevel(logging.DEBUG)
# Make sure all files and paths exists if they are needed
if not config_path or (str(config_path) != "-" and not config_path.exists()):
msg.fail("Config file not found", config_path, exits=1)

2
spacy/cli/benchmark_speed.py
View File

@ -89,7 +89,7 @@ class Quartiles:
def annotate(
nlp: Language, docs: List[Doc], batch_size: Optional[int]
) -> numpy.ndarray:
docs = nlp.pipe(tqdm(docs, unit="doc"), batch_size=batch_size)
docs = nlp.pipe(tqdm(docs, unit="doc", disable=None), batch_size=batch_size)
wps = []
while True:
with time_context() as elapsed:

23
spacy/cli/download.py
View File

@ -10,6 +10,8 @@ from ..util import (
get_installed_models,
get_minor_version,
get_package_version,
is_in_interactive,
is_in_jupyter,
is_package,
is_prerelease_version,
run_command,
@ -85,6 +87,27 @@ def download(
"Download and installation successful",
f"You can now load the package via spacy.load('{model_name}')",
)
if is_in_jupyter():
reload_deps_msg = (
"If you are in a Jupyter or Colab notebook, you may need to "
"restart Python in order to load all the package's dependencies. "
"You can do this by selecting the 'Restart kernel' or 'Restart "
"runtime' option."
)
msg.warn(
"Restart to reload dependencies",
reload_deps_msg,
)
elif is_in_interactive():
reload_deps_msg = (
"If you are in an interactive Python session, you may need to "
"exit and restart Python to load all the package's dependencies. "
"You can exit with Ctrl-D (or Ctrl-Z and Enter on Windows)."
)
msg.warn(
"Restart to reload dependencies",
reload_deps_msg,
)
def get_model_filename(model_name: str, version: str, sdist: bool = False) -> str:

2
spacy/cli/evaluate.py
View File

@ -28,6 +28,7 @@ def evaluate_cli(
displacy_path: Optional[Path] = Opt(None, "--displacy-path", "-dp", help="Directory to output rendered parses as HTML", exists=True, file_okay=False),
displacy_limit: int = Opt(25, "--displacy-limit", "-dl", help="Limit of parses to render as HTML"),
per_component: bool = Opt(False, "--per-component", "-P", help="Return scores per component, only applicable when an output JSON file is specified."),
spans_key: str = Opt("sc", "--spans-key", "-sk", help="Spans key to use when evaluating Doc.spans"),
# fmt: on
):
"""
@ -53,6 +54,7 @@ def evaluate_cli(
displacy_limit=displacy_limit,
per_component=per_component,
silent=False,
spans_key=spans_key,
)

69
spacy/cli/find_function.py Normal file
View File

@ -0,0 +1,69 @@
from typing import Optional, Tuple
from catalogue import RegistryError
from wasabi import msg
from ..util import registry
from ._util import Arg, Opt, app
@app.command("find-function")
def find_function_cli(
# fmt: off
func_name: str = Arg(..., help="Name of the registered function."),
registry_name: Optional[str] = Opt(None, "--registry", "-r", help="Name of the catalogue registry."),
# fmt: on
):
"""
Find the module, path and line number to the file the registered
function is defined in, if available.
func_name (str): Name of the registered function.
registry_name (Optional[str]): Name of the catalogue registry.
DOCS: https://spacy.io/api/cli#find-function
"""
if not registry_name:
registry_names = registry.get_registry_names()
for name in registry_names:
if registry.has(name, func_name):
registry_name = name
break
if not registry_name:
msg.fail(
f"Couldn't find registered function: '{func_name}'",
exits=1,
)
assert registry_name is not None
find_function(func_name, registry_name)
def find_function(func_name: str, registry_name: str) -> Tuple[str, int]:
registry_desc = None
try:
registry_desc = registry.find(registry_name, func_name)
except RegistryError as e:
msg.fail(
f"Couldn't find registered function: '{func_name}' in registry '{registry_name}'",
)
msg.fail(f"{e}", exits=1)
assert registry_desc is not None
registry_path = None
line_no = None
if registry_desc["file"]:
registry_path = registry_desc["file"]
line_no = registry_desc["line_no"]
if not registry_path or not line_no:
msg.fail(
f"Couldn't find path to registered function: '{func_name}' in registry '{registry_name}'",
exits=1,
)
assert registry_path is not None
assert line_no is not None
msg.good(f"Found registered function '{func_name}' at {registry_path}:{line_no}")
return str(registry_path), int(line_no)

4
spacy/cli/find_threshold.py
View File

@ -52,8 +52,8 @@ def find_threshold_cli(
DOCS: https://spacy.io/api/cli#find-threshold
"""
util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
if verbose:
util.logger.setLevel(logging.DEBUG)
import_code(code_path)
find_threshold(
model=model,

6
spacy/cli/init_pipeline.py
View File

@ -90,7 +90,8 @@ def init_pipeline_cli(
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU")
# fmt: on
):
util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
if verbose:
util.logger.setLevel(logging.DEBUG)
overrides = parse_config_overrides(ctx.args)
import_code(code_path)
setup_gpu(use_gpu)
@ -119,7 +120,8 @@ def init_labels_cli(
"""Generate JSON files for the labels in the data. This helps speed up the
training process, since spaCy won't have to preprocess the data to
extract the labels."""
util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
if verbose:
util.logger.setLevel(logging.DEBUG)
if not output_path.exists():
output_path.mkdir(parents=True)
overrides = parse_config_overrides(ctx.args)

61
spacy/cli/package.py
View File

@ -1,5 +1,8 @@
import importlib.metadata
import os
import re
import shutil
import subprocess
import sys
from collections import defaultdict
from pathlib import Path
@ -35,7 +38,7 @@ def package_cli(
specified output directory, and the data will be copied over. If
--create-meta is set and a meta.json already exists in the output directory,
the existing values will be used as the defaults in the command-line prompt.
After packaging, "python setup.py sdist" is run in the package directory,
After packaging, "python -m build --sdist" is run in the package directory,
which will create a .tar.gz archive that can be installed via "pip install".
If additional code files are provided (e.g. Python files containing custom
@ -78,9 +81,17 @@ def package(
input_path = util.ensure_path(input_dir)
output_path = util.ensure_path(output_dir)
meta_path = util.ensure_path(meta_path)
if create_wheel and not has_wheel():
err = "Generating a binary .whl file requires wheel to be installed"
msg.fail(err, "pip install wheel", exits=1)
if create_wheel and not has_wheel() and not has_build():
err = (
"Generating wheels requires 'build' or 'wheel' (deprecated) to be installed"
)
msg.fail(err, "pip install build", exits=1)
if not has_build():
msg.warn(
"Generating packages without the 'build' package is deprecated and "
"will not be supported in the future. To install 'build': pip "
"install build"
)
if not input_path or not input_path.exists():
msg.fail("Can't locate pipeline data", input_path, exits=1)
if not output_path or not output_path.exists():
@ -184,12 +195,37 @@ def package(
msg.good(f"Successfully created package directory '{model_name_v}'", main_path)
if create_sdist:
with util.working_dir(main_path):
util.run_command([sys.executable, "setup.py", "sdist"], capture=False)
# run directly, since util.run_command is not designed to continue
# after a command fails
ret = subprocess.run(
[sys.executable, "-m", "build", ".", "--sdist"],
env=os.environ.copy(),
)
if ret.returncode != 0:
msg.warn(
"Creating sdist with 'python -m build' failed. Falling "
"back to deprecated use of 'python setup.py sdist'"
)
util.run_command([sys.executable, "setup.py", "sdist"], capture=False)
zip_file = main_path / "dist" / f"{model_name_v}{SDIST_SUFFIX}"
msg.good(f"Successfully created zipped Python package", zip_file)
if create_wheel:
with util.working_dir(main_path):
util.run_command([sys.executable, "setup.py", "bdist_wheel"], capture=False)
# run directly, since util.run_command is not designed to continue
# after a command fails
ret = subprocess.run(
[sys.executable, "-m", "build", ".", "--wheel"],
env=os.environ.copy(),
)
if ret.returncode != 0:
msg.warn(
"Creating wheel with 'python -m build' failed. Falling "
"back to deprecated use of 'wheel' with "
"'python setup.py bdist_wheel'"
)
util.run_command(
[sys.executable, "setup.py", "bdist_wheel"], capture=False
)
wheel_name_squashed = re.sub("_+", "_", model_name_v)
wheel = main_path / "dist" / f"{wheel_name_squashed}{WHEEL_SUFFIX}"
msg.good(f"Successfully created binary wheel", wheel)
@ -209,6 +245,17 @@ def has_wheel() -> bool:
return False
def has_build() -> bool:
# it's very likely that there is a local directory named build/ (especially
# in an editable install), so an import check is not sufficient; instead
# check that there is a package version
try:
importlib.metadata.version("build")
return True
except importlib.metadata.PackageNotFoundError: # type: ignore[attr-defined]
return False
def get_third_party_dependencies(
config: Config, exclude: List[str] = util.SimpleFrozenList()
) -> List[str]:
@ -403,7 +450,7 @@ def _format_sources(data: Any) -> str:
if author:
result += " ({})".format(author)
sources.append(result)
return "<br />".join(sources)
return "<br>".join(sources)
def _format_accuracy(data: Dict[str, Any], exclude: List[str] = ["speed"]) -> str:

2
spacy/cli/profile.py
View File

@ -71,7 +71,7 @@ def profile(model: str, inputs: Optional[Path] = None, n_texts: int = 10000) ->
def parse_texts(nlp: Language, texts: Sequence[str]) -> None:
for doc in nlp.pipe(tqdm.tqdm(texts), batch_size=16):
for doc in nlp.pipe(tqdm.tqdm(texts, disable=None), batch_size=16):
pass

218
spacy/cli/project/assets.py
View File

@ -1,217 +1 @@
import os
import re
import shutil
from pathlib import Path
from typing import Any, Dict, Optional
import requests
import typer
from wasabi import msg
from ...util import ensure_path, working_dir
from .._util import (
PROJECT_FILE,
Arg,
Opt,
SimpleFrozenDict,
download_file,
get_checksum,
get_git_version,
git_checkout,
load_project_config,
parse_config_overrides,
project_cli,
)
# Whether assets are extra if `extra` is not set.
EXTRA_DEFAULT = False
@project_cli.command(
"assets",
context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
)
def project_assets_cli(
# fmt: off
ctx: typer.Context, # This is only used to read additional arguments
project_dir: Path = Arg(Path.cwd(), help="Path to cloned project. Defaults to current working directory.", exists=True, file_okay=False),
sparse_checkout: bool = Opt(False, "--sparse", "-S", help="Use sparse checkout for assets provided via Git, to only check out and clone the files needed. Requires Git v22.2+."),
extra: bool = Opt(False, "--extra", "-e", help="Download all assets, including those marked as 'extra'.")
# fmt: on
):
"""Fetch project assets like datasets and pretrained weights. Assets are
defined in the "assets" section of the project.yml. If a checksum is
provided in the project.yml, the file is only downloaded if no local file
with the same checksum exists.
DOCS: https://spacy.io/api/cli#project-assets
"""
overrides = parse_config_overrides(ctx.args)
project_assets(
project_dir,
overrides=overrides,
sparse_checkout=sparse_checkout,
extra=extra,
)
def project_assets(
project_dir: Path,
*,
overrides: Dict[str, Any] = SimpleFrozenDict(),
sparse_checkout: bool = False,
extra: bool = False,
) -> None:
"""Fetch assets for a project using DVC if possible.
project_dir (Path): Path to project directory.
sparse_checkout (bool): Use sparse checkout for assets provided via Git, to only check out and clone the files
needed.
extra (bool): Whether to download all assets, including those marked as 'extra'.
"""
project_path = ensure_path(project_dir)
config = load_project_config(project_path, overrides=overrides)
assets = [
asset
for asset in config.get("assets", [])
if extra or not asset.get("extra", EXTRA_DEFAULT)
]
if not assets:
msg.warn(
f"No assets specified in {PROJECT_FILE} (if assets are marked as extra, download them with --extra)",
exits=0,
)
msg.info(f"Fetching {len(assets)} asset(s)")
for asset in assets:
dest = (project_dir / asset["dest"]).resolve()
checksum = asset.get("checksum")
if "git" in asset:
git_err = (
f"Cloning spaCy project templates requires Git and the 'git' command. "
f"Make sure it's installed and that the executable is available."
)
get_git_version(error=git_err)
if dest.exists():
# If there's already a file, check for checksum
if checksum and checksum == get_checksum(dest):
msg.good(
f"Skipping download with matching checksum: {asset['dest']}"
)
continue
else:
if dest.is_dir():
shutil.rmtree(dest)
else:
dest.unlink()
if "repo" not in asset["git"] or asset["git"]["repo"] is None:
msg.fail(
"A git asset must include 'repo', the repository address.", exits=1
)
if "path" not in asset["git"] or asset["git"]["path"] is None:
msg.fail(
"A git asset must include 'path' - use \"\" to get the entire repository.",
exits=1,
)
git_checkout(
asset["git"]["repo"],
asset["git"]["path"],
dest,
branch=asset["git"].get("branch"),
sparse=sparse_checkout,
)
msg.good(f"Downloaded asset {dest}")
else:
url = asset.get("url")
if not url:
# project.yml defines asset without URL that the user has to place
check_private_asset(dest, checksum)
continue
fetch_asset(project_path, url, dest, checksum)
def check_private_asset(dest: Path, checksum: Optional[str] = None) -> None:
"""Check and validate assets without a URL (private assets that the user
has to provide themselves) and give feedback about the checksum.
dest (Path): Destination path of the asset.
checksum (Optional[str]): Optional checksum of the expected file.
"""
if not Path(dest).exists():
err = f"No URL provided for asset. You need to add this file yourself: {dest}"
msg.warn(err)
else:
if not checksum:
msg.good(f"Asset already exists: {dest}")
elif checksum == get_checksum(dest):
msg.good(f"Asset exists with matching checksum: {dest}")
else:
msg.fail(f"Asset available but with incorrect checksum: {dest}")
def fetch_asset(
project_path: Path, url: str, dest: Path, checksum: Optional[str] = None
) -> None:
"""Fetch an asset from a given URL or path. If a checksum is provided and a
local file exists, it's only re-downloaded if the checksum doesn't match.
project_path (Path): Path to project directory.
url (str): URL or path to asset.
checksum (Optional[str]): Optional expected checksum of local file.
RETURNS (Optional[Path]): The path to the fetched asset or None if fetching
the asset failed.
"""
dest_path = (project_path / dest).resolve()
if dest_path.exists():
# If there's already a file, check for checksum
if checksum:
if checksum == get_checksum(dest_path):
msg.good(f"Skipping download with matching checksum: {dest}")
return
else:
# If there's not a checksum, make sure the file is a possibly valid size
if os.path.getsize(dest_path) == 0:
msg.warn(f"Asset exists but with size of 0 bytes, deleting: {dest}")
os.remove(dest_path)
# We might as well support the user here and create parent directories in
# case the asset dir isn't listed as a dir to create in the project.yml
if not dest_path.parent.exists():
dest_path.parent.mkdir(parents=True)
with working_dir(project_path):
url = convert_asset_url(url)
try:
download_file(url, dest_path)
msg.good(f"Downloaded asset {dest}")
except requests.exceptions.RequestException as e:
if Path(url).exists() and Path(url).is_file():
# If it's a local file, copy to destination
shutil.copy(url, str(dest_path))
msg.good(f"Copied local asset {dest}")
else:
msg.fail(f"Download failed: {dest}", e)
if checksum and checksum != get_checksum(dest_path):
msg.fail(f"Checksum doesn't match value defined in {PROJECT_FILE}: {dest}")
def convert_asset_url(url: str) -> str:
"""Check and convert the asset URL if needed.
url (str): The asset URL.
RETURNS (str): The converted URL.
"""
# If the asset URL is a regular GitHub URL it's likely a mistake
if (
re.match(r"(http(s?)):\/\/github.com", url)
and "releases/download" not in url
and "/raw/" not in url
):
converted = url.replace("github.com", "raw.githubusercontent.com")
converted = re.sub(r"/(tree|blob)/", "/", converted)
msg.warn(
"Downloading from a regular GitHub URL. This will only download "
"the source of the page, not the actual file. Converting the URL "
"to a raw URL.",
converted,
)
return converted
return url
from weasel.cli.assets import *

125
spacy/cli/project/clone.py
View File

@ -1,124 +1 @@
import re
import subprocess
from pathlib import Path
from typing import Optional
from wasabi import msg
from ... import about
from ...util import ensure_path
from .._util import (
COMMAND,
PROJECT_FILE,
Arg,
Opt,
get_git_version,
git_checkout,
git_repo_branch_exists,
project_cli,
)
DEFAULT_REPO = about.__projects__
DEFAULT_PROJECTS_BRANCH = about.__projects_branch__
DEFAULT_BRANCHES = ["main", "master"]
@project_cli.command("clone")
def project_clone_cli(
# fmt: off
name: str = Arg(..., help="The name of the template to clone"),
dest: Optional[Path] = Arg(None, help="Where to clone the project. Defaults to current working directory", exists=False),
repo: str = Opt(DEFAULT_REPO, "--repo", "-r", help="The repository to clone from"),
branch: Optional[str] = Opt(None, "--branch", "-b", help=f"The branch to clone from. If not provided, will attempt {', '.join(DEFAULT_BRANCHES)}"),
sparse_checkout: bool = Opt(False, "--sparse", "-S", help="Use sparse Git checkout to only check out and clone the files needed. Requires Git v22.2+.")
# fmt: on
):
"""Clone a project template from a repository. Calls into "git" and will
only download the files from the given subdirectory. The GitHub repo
defaults to the official spaCy template repo, but can be customized
(including using a private repo).
DOCS: https://spacy.io/api/cli#project-clone
"""
if dest is None:
dest = Path.cwd() / Path(name).parts[-1]
if repo == DEFAULT_REPO and branch is None:
branch = DEFAULT_PROJECTS_BRANCH
if branch is None:
for default_branch in DEFAULT_BRANCHES:
if git_repo_branch_exists(repo, default_branch):
branch = default_branch
break
if branch is None:
default_branches_msg = ", ".join(f"'{b}'" for b in DEFAULT_BRANCHES)
msg.fail(
"No branch provided and attempted default "
f"branches {default_branches_msg} do not exist.",
exits=1,
)
else:
if not git_repo_branch_exists(repo, branch):
msg.fail(f"repo: {repo} (branch: {branch}) does not exist.", exits=1)
assert isinstance(branch, str)
project_clone(name, dest, repo=repo, branch=branch, sparse_checkout=sparse_checkout)
def project_clone(
name: str,
dest: Path,
*,
repo: str = about.__projects__,
branch: str = about.__projects_branch__,
sparse_checkout: bool = False,
) -> None:
"""Clone a project template from a repository.
name (str): Name of subdirectory to clone.
dest (Path): Destination path of cloned project.
repo (str): URL of Git repo containing project templates.
branch (str): The branch to clone from
"""
dest = ensure_path(dest)
check_clone(name, dest, repo)
project_dir = dest.resolve()
repo_name = re.sub(r"(http(s?)):\/\/github.com/", "", repo)
try:
git_checkout(repo, name, dest, branch=branch, sparse=sparse_checkout)
except subprocess.CalledProcessError:
err = f"Could not clone '{name}' from repo '{repo_name}' (branch '{branch}')"
msg.fail(err, exits=1)
msg.good(f"Cloned '{name}' from '{repo_name}' (branch '{branch}')", project_dir)
if not (project_dir / PROJECT_FILE).exists():
msg.warn(f"No {PROJECT_FILE} found in directory")
else:
msg.good(f"Your project is now ready!")
print(f"To fetch the assets, run:\n{COMMAND} project assets {dest}")
def check_clone(name: str, dest: Path, repo: str) -> None:
"""Check and validate that the destination path can be used to clone. Will
check that Git is available and that the destination path is suitable.
name (str): Name of the directory to clone from the repo.
dest (Path): Local destination of cloned directory.
repo (str): URL of the repo to clone from.
"""
git_err = (
f"Cloning spaCy project templates requires Git and the 'git' command. "
f"To clone a project without Git, copy the files from the '{name}' "
f"directory in the {repo} to {dest} manually."
)
get_git_version(error=git_err)
if not dest:
msg.fail(f"Not a valid directory to clone project: {dest}", exits=1)
if dest.exists():
# Directory already exists (not allowed, clone needs to create it)
msg.fail(f"Can't clone project, directory already exists: {dest}", exits=1)
if not dest.parent.exists():
# We're not creating parents, parent dir should exist
msg.fail(
f"Can't clone project, parent directory doesn't exist: {dest.parent}. "
f"Create the necessary folder(s) first before continuing.",
exits=1,
)
from weasel.cli.clone import *

116
spacy/cli/project/document.py
View File

@ -1,115 +1 @@
from pathlib import Path
from wasabi import MarkdownRenderer, msg
from ...util import working_dir
from .._util import PROJECT_FILE, Arg, Opt, load_project_config, project_cli
DOCS_URL = "https://spacy.io"
INTRO_PROJECT = f"""The [`{PROJECT_FILE}`]({PROJECT_FILE}) defines the data assets required by the
project, as well as the available commands and workflows. For details, see the
[spaCy projects documentation]({DOCS_URL}/usage/projects)."""
INTRO_COMMANDS = f"""The following commands are defined by the project. They
can be executed using [`spacy project run [name]`]({DOCS_URL}/api/cli#project-run).
Commands are only re-run if their inputs have changed."""
INTRO_WORKFLOWS = f"""The following workflows are defined by the project. They
can be executed using [`spacy project run [name]`]({DOCS_URL}/api/cli#project-run)
and will run the specified commands in order. Commands are only re-run if their
inputs have changed."""
INTRO_ASSETS = f"""The following assets are defined by the project. They can
be fetched by running [`spacy project assets`]({DOCS_URL}/api/cli#project-assets)
in the project directory."""
# These markers are added to the Markdown and can be used to update the file in
# place if it already exists. Only the auto-generated part will be replaced.
MARKER_START = "<!-- SPACY PROJECT: AUTO-GENERATED DOCS START (do not remove) -->"
MARKER_END = "<!-- SPACY PROJECT: AUTO-GENERATED DOCS END (do not remove) -->"
# If this marker is used in an existing README, it's ignored and not replaced
MARKER_IGNORE = "<!-- SPACY PROJECT: IGNORE -->"
@project_cli.command("document")
def project_document_cli(
# fmt: off
project_dir: Path = Arg(Path.cwd(), help="Path to cloned project. Defaults to current working directory.", exists=True, file_okay=False),
output_file: Path = Opt("-", "--output", "-o", help="Path to output Markdown file for output. Defaults to - for standard output"),
no_emoji: bool = Opt(False, "--no-emoji", "-NE", help="Don't use emoji")
# fmt: on
):
"""
Auto-generate a README.md for a project. If the content is saved to a file,
hidden markers are added so you can add custom content before or after the
auto-generated section and only the auto-generated docs will be replaced
when you re-run the command.
DOCS: https://spacy.io/api/cli#project-document
"""
project_document(project_dir, output_file, no_emoji=no_emoji)
def project_document(
project_dir: Path, output_file: Path, *, no_emoji: bool = False
) -> None:
is_stdout = str(output_file) == "-"
config = load_project_config(project_dir)
md = MarkdownRenderer(no_emoji=no_emoji)
md.add(MARKER_START)
title = config.get("title")
description = config.get("description")
md.add(md.title(1, f"spaCy Project{f': {title}' if title else ''}", "🪐"))
if description:
md.add(description)
md.add(md.title(2, PROJECT_FILE, "📋"))
md.add(INTRO_PROJECT)
# Commands
cmds = config.get("commands", [])
data = [(md.code(cmd["name"]), cmd.get("help", "")) for cmd in cmds]
if data:
md.add(md.title(3, "Commands", "⏯"))
md.add(INTRO_COMMANDS)
md.add(md.table(data, ["Command", "Description"]))
# Workflows
wfs = config.get("workflows", {}).items()
data = [(md.code(n), " &rarr; ".join(md.code(w) for w in stp)) for n, stp in wfs]
if data:
md.add(md.title(3, "Workflows", "⏭"))
md.add(INTRO_WORKFLOWS)
md.add(md.table(data, ["Workflow", "Steps"]))
# Assets
assets = config.get("assets", [])
data = []
for a in assets:
source = "Git" if a.get("git") else "URL" if a.get("url") else "Local"
dest_path = a["dest"]
dest = md.code(dest_path)
if source == "Local":
# Only link assets if they're in the repo
with working_dir(project_dir) as p:
if (p / dest_path).exists():
dest = md.link(dest, dest_path)
data.append((dest, source, a.get("description", "")))
if data:
md.add(md.title(3, "Assets", "🗂"))
md.add(INTRO_ASSETS)
md.add(md.table(data, ["File", "Source", "Description"]))
md.add(MARKER_END)
# Output result
if is_stdout:
print(md.text)
else:
content = md.text
if output_file.exists():
with output_file.open("r", encoding="utf8") as f:
existing = f.read()
if MARKER_IGNORE in existing:
msg.warn("Found ignore marker in existing file: skipping", output_file)
return
if MARKER_START in existing and MARKER_END in existing:
msg.info("Found existing file: only replacing auto-generated docs")
before = existing.split(MARKER_START)[0]
after = existing.split(MARKER_END)[1]
content = f"{before}{content}{after}"
else:
msg.warn("Replacing existing file")
with output_file.open("w", encoding="utf8") as f:
f.write(content)
msg.good("Saved project documentation", output_file)
from weasel.cli.document import *

221
spacy/cli/project/dvc.py
View File

@ -1,220 +1 @@
"""This module contains helpers and subcommands for integrating spaCy projects
with Data Version Controk (DVC). https://dvc.org"""
import subprocess
from pathlib import Path
from typing import Any, Dict, Iterable, List, Optional
from wasabi import msg
from ...util import (
SimpleFrozenList,
join_command,
run_command,
split_command,
working_dir,
)
from .._util import (
COMMAND,
NAME,
PROJECT_FILE,
Arg,
Opt,
get_hash,
load_project_config,
project_cli,
)
DVC_CONFIG = "dvc.yaml"
DVC_DIR = ".dvc"
UPDATE_COMMAND = "dvc"
DVC_CONFIG_COMMENT = f"""# This file is auto-generated by spaCy based on your {PROJECT_FILE}. If you've
# edited your {PROJECT_FILE}, you can regenerate this file by running:
# {COMMAND} project {UPDATE_COMMAND}"""
@project_cli.command(UPDATE_COMMAND)
def project_update_dvc_cli(
# fmt: off
project_dir: Path = Arg(Path.cwd(), help="Location of project directory. Defaults to current working directory.", exists=True, file_okay=False),
workflow: Optional[str] = Arg(None, help=f"Name of workflow defined in {PROJECT_FILE}. Defaults to first workflow if not set."),
verbose: bool = Opt(False, "--verbose", "-V", help="Print more info"),
quiet: bool = Opt(False, "--quiet", "-q", help="Print less info"),
force: bool = Opt(False, "--force", "-F", help="Force update DVC config"),
# fmt: on
):
"""Auto-generate Data Version Control (DVC) config. A DVC
project can only define one pipeline, so you need to specify one workflow
defined in the project.yml. If no workflow is specified, the first defined
workflow is used. The DVC config will only be updated if the project.yml
changed.
DOCS: https://spacy.io/api/cli#project-dvc
"""
project_update_dvc(project_dir, workflow, verbose=verbose, quiet=quiet, force=force)
def project_update_dvc(
project_dir: Path,
workflow: Optional[str] = None,
*,
verbose: bool = False,
quiet: bool = False,
force: bool = False,
) -> None:
"""Update the auto-generated Data Version Control (DVC) config file. A DVC
project can only define one pipeline, so you need to specify one workflow
defined in the project.yml. Will only update the file if the checksum changed.
project_dir (Path): The project directory.
workflow (Optional[str]): Optional name of workflow defined in project.yml.
If not set, the first workflow will be used.
verbose (bool): Print more info.
quiet (bool): Print less info.
force (bool): Force update DVC config.
"""
config = load_project_config(project_dir)
updated = update_dvc_config(
project_dir, config, workflow, verbose=verbose, quiet=quiet, force=force
)
help_msg = "To execute the workflow with DVC, run: dvc repro"
if updated:
msg.good(f"Updated DVC config from {PROJECT_FILE}", help_msg)
else:
msg.info(f"No changes found in {PROJECT_FILE}, no update needed", help_msg)
def update_dvc_config(
path: Path,
config: Dict[str, Any],
workflow: Optional[str] = None,
verbose: bool = False,
quiet: bool = False,
force: bool = False,
) -> bool:
"""Re-run the DVC commands in dry mode and update dvc.yaml file in the
project directory. The file is auto-generated based on the config. The
first line of the auto-generated file specifies the hash of the config
dict, so if any of the config values change, the DVC config is regenerated.
path (Path): The path to the project directory.
config (Dict[str, Any]): The loaded project.yml.
verbose (bool): Whether to print additional info (via DVC).
quiet (bool): Don't output anything (via DVC).
force (bool): Force update, even if hashes match.
RETURNS (bool): Whether the DVC config file was updated.
"""
ensure_dvc(path)
workflows = config.get("workflows", {})
workflow_names = list(workflows.keys())
check_workflows(workflow_names, workflow)
if not workflow:
workflow = workflow_names[0]
config_hash = get_hash(config)
path = path.resolve()
dvc_config_path = path / DVC_CONFIG
if dvc_config_path.exists():
# Check if the file was generated using the current config, if not, redo
with dvc_config_path.open("r", encoding="utf8") as f:
ref_hash = f.readline().strip().replace("# ", "")
if ref_hash == config_hash and not force:
return False # Nothing has changed in project.yml, don't need to update
dvc_config_path.unlink()
dvc_commands = []
config_commands = {cmd["name"]: cmd for cmd in config.get("commands", [])}
# some flags that apply to every command
flags = []
if verbose:
flags.append("--verbose")
if quiet:
flags.append("--quiet")
for name in workflows[workflow]:
command = config_commands[name]
deps = command.get("deps", [])
outputs = command.get("outputs", [])
outputs_no_cache = command.get("outputs_no_cache", [])
if not deps and not outputs and not outputs_no_cache:
continue
# Default to the working dir as the project path since dvc.yaml is auto-generated
# and we don't want arbitrary paths in there
project_cmd = ["python", "-m", NAME, "project", "run", name]
deps_cmd = [c for cl in [["-d", p] for p in deps] for c in cl]
outputs_cmd = [c for cl in [["-o", p] for p in outputs] for c in cl]
outputs_nc_cmd = [c for cl in [["-O", p] for p in outputs_no_cache] for c in cl]
dvc_cmd = ["run", *flags, "-n", name, "-w", str(path), "--no-exec"]
if command.get("no_skip"):
dvc_cmd.append("--always-changed")
full_cmd = [*dvc_cmd, *deps_cmd, *outputs_cmd, *outputs_nc_cmd, *project_cmd]
dvc_commands.append(join_command(full_cmd))
if not dvc_commands:
# If we don't check for this, then there will be an error when reading the
# config, since DVC wouldn't create it.
msg.fail(
"No usable commands for DVC found. This can happen if none of your "
"commands have dependencies or outputs.",
exits=1,
)
with working_dir(path):
for c in dvc_commands:
dvc_command = "dvc " + c
run_command(dvc_command)
with dvc_config_path.open("r+", encoding="utf8") as f:
content = f.read()
f.seek(0, 0)
f.write(f"# {config_hash}\n{DVC_CONFIG_COMMENT}\n{content}")
return True
def check_workflows(workflows: List[str], workflow: Optional[str] = None) -> None:
"""Validate workflows provided in project.yml and check that a given
workflow can be used to generate a DVC config.
workflows (List[str]): Names of the available workflows.
workflow (Optional[str]): The name of the workflow to convert.
"""
if not workflows:
msg.fail(
f"No workflows defined in {PROJECT_FILE}. To generate a DVC config, "
f"define at least one list of commands.",
exits=1,
)
if workflow is not None and workflow not in workflows:
msg.fail(
f"Workflow '{workflow}' not defined in {PROJECT_FILE}. "
f"Available workflows: {', '.join(workflows)}",
exits=1,
)
if not workflow:
msg.warn(
f"No workflow specified for DVC pipeline. Using the first workflow "
f"defined in {PROJECT_FILE}: '{workflows[0]}'"
)
def ensure_dvc(project_dir: Path) -> None:
"""Ensure that the "dvc" command is available and that the current project
directory is an initialized DVC project.
"""
try:
subprocess.run(["dvc", "--version"], stdout=subprocess.DEVNULL)
except Exception:
msg.fail(
"To use spaCy projects with DVC (Data Version Control), DVC needs "
"to be installed and the 'dvc' command needs to be available",
"You can install the Python package from pip (pip install dvc) or "
"conda (conda install -c conda-forge dvc). For more details, see the "
"documentation: https://dvc.org/doc/install",
exits=1,
)
if not (project_dir / ".dvc").exists():
msg.fail(
"Project not initialized as a DVC project",
"To initialize a DVC project, you can run 'dvc init' in the project "
"directory. For more details, see the documentation: "
"https://dvc.org/doc/command-reference/init",
exits=1,
)
from weasel.cli.dvc import *

68
spacy/cli/project/pull.py
View File

@ -1,67 +1 @@
from pathlib import Path
from wasabi import msg
from .._util import Arg, load_project_config, logger, project_cli
from .remote_storage import RemoteStorage, get_command_hash
from .run import update_lockfile
@project_cli.command("pull")
def project_pull_cli(
# fmt: off
remote: str = Arg("default", help="Name or path of remote storage"),
project_dir: Path = Arg(Path.cwd(), help="Location of project directory. Defaults to current working directory.", exists=True, file_okay=False),
# fmt: on
):
"""Retrieve available precomputed outputs from a remote storage.
You can alias remotes in your project.yml by mapping them to storage paths.
A storage can be anything that the smart-open library can upload to, e.g.
AWS, Google Cloud Storage, SSH, local directories etc.
DOCS: https://spacy.io/api/cli#project-pull
"""
for url, output_path in project_pull(project_dir, remote):
if url is not None:
msg.good(f"Pulled {output_path} from {url}")
def project_pull(project_dir: Path, remote: str, *, verbose: bool = False):
# TODO: We don't have tests for this :(. It would take a bit of mockery to
# set up. I guess see if it breaks first?
config = load_project_config(project_dir)
if remote in config.get("remotes", {}):
remote = config["remotes"][remote]
storage = RemoteStorage(project_dir, remote)
commands = list(config.get("commands", []))
# We use a while loop here because we don't know how the commands
# will be ordered. A command might need dependencies from one that's later
# in the list.
while commands:
for i, cmd in enumerate(list(commands)):
logger.debug("CMD: %s.", cmd["name"])
deps = [project_dir / dep for dep in cmd.get("deps", [])]
if all(dep.exists() for dep in deps):
cmd_hash = get_command_hash("", "", deps, cmd["script"])
for output_path in cmd.get("outputs", []):
url = storage.pull(output_path, command_hash=cmd_hash)
logger.debug(
"URL: %s for %s with command hash %s",
url,
output_path,
cmd_hash,
)
yield url, output_path
out_locs = [project_dir / out for out in cmd.get("outputs", [])]
if all(loc.exists() for loc in out_locs):
update_lockfile(project_dir, cmd)
# We remove the command from the list here, and break, so that
# we iterate over the loop again.
commands.pop(i)
break
else:
logger.debug("Dependency missing. Skipping %s outputs.", cmd["name"])
else:
# If we didn't break the for loop, break the while loop.
break
from weasel.cli.pull import *

70
spacy/cli/project/push.py
View File

@ -1,69 +1 @@
from pathlib import Path
from wasabi import msg
from .._util import Arg, load_project_config, logger, project_cli
from .remote_storage import RemoteStorage, get_command_hash, get_content_hash
@project_cli.command("push")
def project_push_cli(
# fmt: off
remote: str = Arg("default", help="Name or path of remote storage"),
project_dir: Path = Arg(Path.cwd(), help="Location of project directory. Defaults to current working directory.", exists=True, file_okay=False),
# fmt: on
):
"""Persist outputs to a remote storage. You can alias remotes in your
project.yml by mapping them to storage paths. A storage can be anything that
the smart-open library can upload to, e.g. AWS, Google Cloud Storage, SSH,
local directories etc.
DOCS: https://spacy.io/api/cli#project-push
"""
for output_path, url in project_push(project_dir, remote):
if url is None:
msg.info(f"Skipping {output_path}")
else:
msg.good(f"Pushed {output_path} to {url}")
def project_push(project_dir: Path, remote: str):
"""Persist outputs to a remote storage. You can alias remotes in your project.yml
by mapping them to storage paths. A storage can be anything that the smart-open
library can upload to, e.g. gcs, aws, ssh, local directories etc
"""
config = load_project_config(project_dir)
if remote in config.get("remotes", {}):
remote = config["remotes"][remote]
storage = RemoteStorage(project_dir, remote)
for cmd in config.get("commands", []):
logger.debug("CMD: %s", cmd["name"])
deps = [project_dir / dep for dep in cmd.get("deps", [])]
if any(not dep.exists() for dep in deps):
logger.debug("Dependency missing. Skipping %s outputs", cmd["name"])
continue
cmd_hash = get_command_hash(
"", "", [project_dir / dep for dep in cmd.get("deps", [])], cmd["script"]
)
logger.debug("CMD_HASH: %s", cmd_hash)
for output_path in cmd.get("outputs", []):
output_loc = project_dir / output_path
if output_loc.exists() and _is_not_empty_dir(output_loc):
url = storage.push(
output_path,
command_hash=cmd_hash,
content_hash=get_content_hash(output_loc),
)
logger.debug(
"URL: %s for output %s with cmd_hash %s", url, output_path, cmd_hash
)
yield output_path, url
def _is_not_empty_dir(loc: Path):
if not loc.is_dir():
return True
elif any(_is_not_empty_dir(child) for child in loc.iterdir()):
return True
else:
return False
from weasel.cli.push import *

213
spacy/cli/project/remote_storage.py
View File

@ -1,212 +1 @@
import hashlib
import os
import site
import tarfile
import urllib.parse
from pathlib import Path
from typing import TYPE_CHECKING, Dict, List, Optional
from wasabi import msg
from ... import about
from ...errors import Errors
from ...git_info import GIT_VERSION
from ...util import ENV_VARS, check_bool_env_var, get_minor_version
from .._util import (
download_file,
ensure_pathy,
get_checksum,
get_hash,
make_tempdir,
upload_file,
)
if TYPE_CHECKING:
from pathy import FluidPath # noqa: F401
class RemoteStorage:
"""Push and pull outputs to and from a remote file storage.
Remotes can be anything that `smart-open` can support: AWS, GCS, file system,
ssh, etc.
"""
def __init__(self, project_root: Path, url: str, *, compression="gz"):
self.root = project_root
self.url = ensure_pathy(url)
self.compression = compression
def push(self, path: Path, command_hash: str, content_hash: str) -> "FluidPath":
"""Compress a file or directory within a project and upload it to a remote
storage. If an object exists at the full URL, nothing is done.
Within the remote storage, files are addressed by their project path
(url encoded) and two user-supplied hashes, representing their creation
context and their file contents. If the URL already exists, the data is
not uploaded. Paths are archived and compressed prior to upload.
"""
loc = self.root / path
if not loc.exists():
raise IOError(f"Cannot push {loc}: does not exist.")
url = self.make_url(path, command_hash, content_hash)
if url.exists():
return url
tmp: Path
with make_tempdir() as tmp:
tar_loc = tmp / self.encode_name(str(path))
mode_string = f"w:{self.compression}" if self.compression else "w"
with tarfile.open(tar_loc, mode=mode_string) as tar_file:
tar_file.add(str(loc), arcname=str(path))
upload_file(tar_loc, url)
return url
def pull(
self,
path: Path,
*,
command_hash: Optional[str] = None,
content_hash: Optional[str] = None,
) -> Optional["FluidPath"]:
"""Retrieve a file from the remote cache. If the file already exists,
nothing is done.
If the command_hash and/or content_hash are specified, only matching
results are returned. If no results are available, an error is raised.
"""
dest = self.root / path
if dest.exists():
return None
url = self.find(path, command_hash=command_hash, content_hash=content_hash)
if url is None:
return url
else:
# Make sure the destination exists
if not dest.parent.exists():
dest.parent.mkdir(parents=True)
tmp: Path
with make_tempdir() as tmp:
tar_loc = tmp / url.parts[-1]
download_file(url, tar_loc)
mode_string = f"r:{self.compression}" if self.compression else "r"
with tarfile.open(tar_loc, mode=mode_string) as tar_file:
# This requires that the path is added correctly, relative
# to root. This is how we set things up in push()
# Disallow paths outside the current directory for the tar
# file (CVE-2007-4559, directory traversal vulnerability)
def is_within_directory(directory, target):
abs_directory = os.path.abspath(directory)
abs_target = os.path.abspath(target)
prefix = os.path.commonprefix([abs_directory, abs_target])
return prefix == abs_directory
def safe_extract(tar, path):
for member in tar.getmembers():
member_path = os.path.join(path, member.name)
if not is_within_directory(path, member_path):
raise ValueError(Errors.E852)
tar.extractall(path)
safe_extract(tar_file, self.root)
return url
def find(
self,
path: Path,
*,
command_hash: Optional[str] = None,
content_hash: Optional[str] = None,
) -> Optional["FluidPath"]:
"""Find the best matching version of a file within the storage,
or `None` if no match can be found. If both the creation and content hash
are specified, only exact matches will be returned. Otherwise, the most
recent matching file is preferred.
"""
name = self.encode_name(str(path))
urls = []
if command_hash is not None and content_hash is not None:
url = self.url / name / command_hash / content_hash
urls = [url] if url.exists() else []
elif command_hash is not None:
if (self.url / name / command_hash).exists():
urls = list((self.url / name / command_hash).iterdir())
else:
if (self.url / name).exists():
for sub_dir in (self.url / name).iterdir():
urls.extend(sub_dir.iterdir())
if content_hash is not None:
urls = [url for url in urls if url.parts[-1] == content_hash]
if len(urls) >= 2:
try:
urls.sort(key=lambda x: x.stat().last_modified) # type: ignore
except Exception:
msg.warn(
"Unable to sort remote files by last modified. The file(s) "
"pulled from the cache may not be the most recent."
)
return urls[-1] if urls else None
def make_url(self, path: Path, command_hash: str, content_hash: str) -> "FluidPath":
"""Construct a URL from a subpath, a creation hash and a content hash."""
return self.url / self.encode_name(str(path)) / command_hash / content_hash
def encode_name(self, name: str) -> str:
"""Encode a subpath into a URL-safe name."""
return urllib.parse.quote_plus(name)
def get_content_hash(loc: Path) -> str:
return get_checksum(loc)
def get_command_hash(
site_hash: str, env_hash: str, deps: List[Path], cmd: List[str]
) -> str:
"""Create a hash representing the execution of a command. This includes the
currently installed packages, whatever environment variables have been marked
as relevant, and the command.
"""
if check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION):
spacy_v = GIT_VERSION
else:
spacy_v = str(get_minor_version(about.__version__) or "")
dep_checksums = [get_checksum(dep) for dep in sorted(deps)]
hashes = [spacy_v, site_hash, env_hash] + dep_checksums
hashes.extend(cmd)
creation_bytes = "".join(hashes).encode("utf8")
return hashlib.md5(creation_bytes).hexdigest()
def get_site_hash():
"""Hash the current Python environment's site-packages contents, including
the name and version of the libraries. The list we're hashing is what
`pip freeze` would output.
"""
site_dirs = site.getsitepackages()
if site.ENABLE_USER_SITE:
site_dirs.extend(site.getusersitepackages())
packages = set()
for site_dir in site_dirs:
site_dir = Path(site_dir)
for subpath in site_dir.iterdir():
if subpath.parts[-1].endswith("dist-info"):
packages.add(subpath.parts[-1].replace(".dist-info", ""))
package_bytes = "".join(sorted(packages)).encode("utf8")
return hashlib.md5sum(package_bytes).hexdigest()
def get_env_hash(env: Dict[str, str]) -> str:
"""Construct a hash of the environment variables that will be passed into
the commands.
Values in the env dict may be references to the current os.environ, using
the syntax $ENV_VAR to mean os.environ[ENV_VAR]
"""
env_vars = {}
for key, value in env.items():
if value.startswith("$"):
env_vars[key] = os.environ.get(value[1:], "")
else:
env_vars[key] = value
return get_hash(env_vars)
from weasel.cli.remote_storage import *

380
spacy/cli/project/run.py
View File

@ -1,379 +1 @@
import os.path
import sys
from pathlib import Path
from typing import Any, Dict, Iterable, List, Optional, Sequence, Tuple
import srsly
import typer
from wasabi import msg
from wasabi.util import locale_escape
from ... import about
from ...git_info import GIT_VERSION
from ...util import (
ENV_VARS,
SimpleFrozenDict,
SimpleFrozenList,
check_bool_env_var,
is_cwd,
is_minor_version_match,
join_command,
run_command,
split_command,
working_dir,
)
from .._util import (
COMMAND,
PROJECT_FILE,
PROJECT_LOCK,
Arg,
Opt,
get_checksum,
get_hash,
load_project_config,
parse_config_overrides,
project_cli,
)
@project_cli.command(
"run", context_settings={"allow_extra_args": True, "ignore_unknown_options": True}
)
def project_run_cli(
# fmt: off
ctx: typer.Context, # This is only used to read additional arguments
subcommand: str = Arg(None, help=f"Name of command defined in the {PROJECT_FILE}"),
project_dir: Path = Arg(Path.cwd(), help="Location of project directory. Defaults to current working directory.", exists=True, file_okay=False),
force: bool = Opt(False, "--force", "-F", help="Force re-running steps, even if nothing changed"),
dry: bool = Opt(False, "--dry", "-D", help="Perform a dry run and don't execute scripts"),
show_help: bool = Opt(False, "--help", help="Show help message and available subcommands")
# fmt: on
):
"""Run a named command or workflow defined in the project.yml. If a workflow
name is specified, all commands in the workflow are run, in order. If
commands define dependencies and/or outputs, they will only be re-run if
state has changed.
DOCS: https://spacy.io/api/cli#project-run
"""
if show_help or not subcommand:
print_run_help(project_dir, subcommand)
else:
overrides = parse_config_overrides(ctx.args)
project_run(project_dir, subcommand, overrides=overrides, force=force, dry=dry)
def project_run(
project_dir: Path,
subcommand: str,
*,
overrides: Dict[str, Any] = SimpleFrozenDict(),
force: bool = False,
dry: bool = False,
capture: bool = False,
skip_requirements_check: bool = False,
) -> None:
"""Run a named script defined in the project.yml. If the script is part
of the default pipeline (defined in the "run" section), DVC is used to
execute the command, so it can determine whether to rerun it. It then
calls into "exec" to execute it.
project_dir (Path): Path to project directory.
subcommand (str): Name of command to run.
overrides (Dict[str, Any]): Optional config overrides.
force (bool): Force re-running, even if nothing changed.
dry (bool): Perform a dry run and don't execute commands.
capture (bool): Whether to capture the output and errors of individual commands.
If False, the stdout and stderr will not be redirected, and if there's an error,
sys.exit will be called with the return code. You should use capture=False
when you want to turn over execution to the command, and capture=True
when you want to run the command more like a function.
skip_requirements_check (bool): Whether to skip the requirements check.
"""
config = load_project_config(project_dir, overrides=overrides)
commands = {cmd["name"]: cmd for cmd in config.get("commands", [])}
workflows = config.get("workflows", {})
validate_subcommand(list(commands.keys()), list(workflows.keys()), subcommand)
req_path = project_dir / "requirements.txt"
if not skip_requirements_check:
if config.get("check_requirements", True) and os.path.exists(req_path):
with req_path.open() as requirements_file:
_check_requirements([req.strip() for req in requirements_file])
if subcommand in workflows:
msg.info(f"Running workflow '{subcommand}'")
for cmd in workflows[subcommand]:
project_run(
project_dir,
cmd,
overrides=overrides,
force=force,
dry=dry,
capture=capture,
skip_requirements_check=True,
)
else:
cmd = commands[subcommand]
for dep in cmd.get("deps", []):
if not (project_dir / dep).exists():
err = f"Missing dependency specified by command '{subcommand}': {dep}"
err_help = "Maybe you forgot to run the 'project assets' command or a previous step?"
err_exits = 1 if not dry else None
msg.fail(err, err_help, exits=err_exits)
check_spacy_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION)
with working_dir(project_dir) as current_dir:
msg.divider(subcommand)
rerun = check_rerun(current_dir, cmd, check_spacy_commit=check_spacy_commit)
if not rerun and not force:
msg.info(f"Skipping '{cmd['name']}': nothing changed")
else:
run_commands(cmd["script"], dry=dry, capture=capture)
if not dry:
update_lockfile(current_dir, cmd)
def print_run_help(project_dir: Path, subcommand: Optional[str] = None) -> None:
"""Simulate a CLI help prompt using the info available in the project.yml.
project_dir (Path): The project directory.
subcommand (Optional[str]): The subcommand or None. If a subcommand is
provided, the subcommand help is shown. Otherwise, the top-level help
and a list of available commands is printed.
"""
config = load_project_config(project_dir)
config_commands = config.get("commands", [])
commands = {cmd["name"]: cmd for cmd in config_commands}
workflows = config.get("workflows", {})
project_loc = "" if is_cwd(project_dir) else project_dir
if subcommand:
validate_subcommand(list(commands.keys()), list(workflows.keys()), subcommand)
print(f"Usage: {COMMAND} project run {subcommand} {project_loc}")
if subcommand in commands:
help_text = commands[subcommand].get("help")
if help_text:
print(f"\n{help_text}\n")
elif subcommand in workflows:
steps = workflows[subcommand]
print(f"\nWorkflow consisting of {len(steps)} commands:")
steps_data = [
(f"{i + 1}. {step}", commands[step].get("help", ""))
for i, step in enumerate(steps)
]
msg.table(steps_data)
help_cmd = f"{COMMAND} project run [COMMAND] {project_loc} --help"
print(f"For command details, run: {help_cmd}")
else:
print("")
title = config.get("title")
if title:
print(f"{locale_escape(title)}\n")
if config_commands:
print(f"Available commands in {PROJECT_FILE}")
print(f"Usage: {COMMAND} project run [COMMAND] {project_loc}")
msg.table([(cmd["name"], cmd.get("help", "")) for cmd in config_commands])
if workflows:
print(f"Available workflows in {PROJECT_FILE}")
print(f"Usage: {COMMAND} project run [WORKFLOW] {project_loc}")
msg.table([(name, " -> ".join(steps)) for name, steps in workflows.items()])
def run_commands(
commands: Iterable[str] = SimpleFrozenList(),
silent: bool = False,
dry: bool = False,
capture: bool = False,
) -> None:
"""Run a sequence of commands in a subprocess, in order.
commands (List[str]): The string commands.
silent (bool): Don't print the commands.
dry (bool): Perform a dry run and don't execut anything.
capture (bool): Whether to capture the output and errors of individual commands.
If False, the stdout and stderr will not be redirected, and if there's an error,
sys.exit will be called with the return code. You should use capture=False
when you want to turn over execution to the command, and capture=True
when you want to run the command more like a function.
"""
for c in commands:
command = split_command(c)
# Not sure if this is needed or a good idea. Motivation: users may often
# use commands in their config that reference "python" and we want to
# make sure that it's always executing the same Python that spaCy is
# executed with and the pip in the same env, not some other Python/pip.
# Also ensures cross-compatibility if user 1 writes "python3" (because
# that's how it's set up on their system), and user 2 without the
# shortcut tries to re-run the command.
if len(command) and command[0] in ("python", "python3"):
command[0] = sys.executable
elif len(command) and command[0] in ("pip", "pip3"):
command = [sys.executable, "-m", "pip", *command[1:]]
if not silent:
print(f"Running command: {join_command(command)}")
if not dry:
run_command(command, capture=capture)
def validate_subcommand(
commands: Sequence[str], workflows: Sequence[str], subcommand: str
) -> None:
"""Check that a subcommand is valid and defined. Raises an error otherwise.
commands (Sequence[str]): The available commands.
subcommand (str): The subcommand.
"""
if not commands and not workflows:
msg.fail(f"No commands or workflows defined in {PROJECT_FILE}", exits=1)
if subcommand not in commands and subcommand not in workflows:
help_msg = []
if subcommand in ["assets", "asset"]:
help_msg.append("Did you mean to run: python -m spacy project assets?")
if commands:
help_msg.append(f"Available commands: {', '.join(commands)}")
if workflows:
help_msg.append(f"Available workflows: {', '.join(workflows)}")
msg.fail(
f"Can't find command or workflow '{subcommand}' in {PROJECT_FILE}",
". ".join(help_msg),
exits=1,
)
def check_rerun(
project_dir: Path,
command: Dict[str, Any],
*,
check_spacy_version: bool = True,
check_spacy_commit: bool = False,
) -> bool:
"""Check if a command should be rerun because its settings or inputs/outputs
changed.
project_dir (Path): The current project directory.
command (Dict[str, Any]): The command, as defined in the project.yml.
strict_version (bool):
RETURNS (bool): Whether to re-run the command.
"""
# Always rerun if no-skip is set
if command.get("no_skip", False):
return True
lock_path = project_dir / PROJECT_LOCK
if not lock_path.exists(): # We don't have a lockfile, run command
return True
data = srsly.read_yaml(lock_path)
if command["name"] not in data: # We don't have info about this command
return True
entry = data[command["name"]]
# Always run commands with no outputs (otherwise they'd always be skipped)
if not entry.get("outs", []):
return True
# Always rerun if spaCy version or commit hash changed
spacy_v = entry.get("spacy_version")
commit = entry.get("spacy_git_version")
if check_spacy_version and not is_minor_version_match(spacy_v, about.__version__):
info = f"({spacy_v} in {PROJECT_LOCK}, {about.__version__} current)"
msg.info(f"Re-running '{command['name']}': spaCy minor version changed {info}")
return True
if check_spacy_commit and commit != GIT_VERSION:
info = f"({commit} in {PROJECT_LOCK}, {GIT_VERSION} current)"
msg.info(f"Re-running '{command['name']}': spaCy commit changed {info}")
return True
# If the entry in the lockfile matches the lockfile entry that would be
# generated from the current command, we don't rerun because it means that
# all inputs/outputs, hashes and scripts are the same and nothing changed
lock_entry = get_lock_entry(project_dir, command)
exclude = ["spacy_version", "spacy_git_version"]
return get_hash(lock_entry, exclude=exclude) != get_hash(entry, exclude=exclude)
def update_lockfile(project_dir: Path, command: Dict[str, Any]) -> None:
"""Update the lockfile after running a command. Will create a lockfile if
it doesn't yet exist and will add an entry for the current command, its
script and dependencies/outputs.
project_dir (Path): The current project directory.
command (Dict[str, Any]): The command, as defined in the project.yml.
"""
lock_path = project_dir / PROJECT_LOCK
if not lock_path.exists():
srsly.write_yaml(lock_path, {})
data = {}
else:
data = srsly.read_yaml(lock_path)
data[command["name"]] = get_lock_entry(project_dir, command)
srsly.write_yaml(lock_path, data)
def get_lock_entry(project_dir: Path, command: Dict[str, Any]) -> Dict[str, Any]:
"""Get a lockfile entry for a given command. An entry includes the command,
the script (command steps) and a list of dependencies and outputs with
their paths and file hashes, if available. The format is based on the
dvc.lock files, to keep things consistent.
project_dir (Path): The current project directory.
command (Dict[str, Any]): The command, as defined in the project.yml.
RETURNS (Dict[str, Any]): The lockfile entry.
"""
deps = get_fileinfo(project_dir, command.get("deps", []))
outs = get_fileinfo(project_dir, command.get("outputs", []))
outs_nc = get_fileinfo(project_dir, command.get("outputs_no_cache", []))
return {
"cmd": f"{COMMAND} run {command['name']}",
"script": command["script"],
"deps": deps,
"outs": [*outs, *outs_nc],
"spacy_version": about.__version__,
"spacy_git_version": GIT_VERSION,
}
def get_fileinfo(project_dir: Path, paths: List[str]) -> List[Dict[str, Optional[str]]]:
"""Generate the file information for a list of paths (dependencies, outputs).
Includes the file path and the file's checksum.
project_dir (Path): The current project directory.
paths (List[str]): The file paths.
RETURNS (List[Dict[str, str]]): The lockfile entry for a file.
"""
data = []
for path in paths:
file_path = project_dir / path
md5 = get_checksum(file_path) if file_path.exists() else None
data.append({"path": path, "md5": md5})
return data
def _check_requirements(requirements: List[str]) -> Tuple[bool, bool]:
"""Checks whether requirements are installed and free of version conflicts.
requirements (List[str]): List of requirements.
RETURNS (Tuple[bool, bool]): Whether (1) any packages couldn't be imported, (2) any packages with version conflicts
exist.
"""
import pkg_resources
failed_pkgs_msgs: List[str] = []
conflicting_pkgs_msgs: List[str] = []
for req in requirements:
try:
pkg_resources.require(req)
except pkg_resources.DistributionNotFound as dnf:
failed_pkgs_msgs.append(dnf.report())
except pkg_resources.VersionConflict as vc:
conflicting_pkgs_msgs.append(vc.report())
except Exception:
msg.warn(
f"Unable to check requirement: {req} "
"Checks are currently limited to requirement specifiers "
"(PEP 508)"
)
if len(failed_pkgs_msgs) or len(conflicting_pkgs_msgs):
msg.warn(
title="Missing requirements or requirement conflicts detected. Make sure your Python environment is set up "
"correctly and you installed all requirements specified in your project's requirements.txt: "
)
for pgk_msg in failed_pkgs_msgs + conflicting_pkgs_msgs:
msg.text(pgk_msg)
return len(failed_pkgs_msgs) > 0, len(conflicting_pkgs_msgs) > 0
from weasel.cli.run import *

17
spacy/cli/templates/quickstart_training.jinja
View File

@ -271,8 +271,9 @@ grad_factor = 1.0
@layers = "reduce_mean.v1"
[components.textcat.model.linear_model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = true
length = 262144
ngram_size = 1
no_output_layer = false
@ -308,8 +309,9 @@ grad_factor = 1.0
@layers = "reduce_mean.v1"
[components.textcat_multilabel.model.linear_model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = false
length = 262144
ngram_size = 1
no_output_layer = false
@ -542,14 +544,15 @@ nO = null
width = ${components.tok2vec.model.encode.width}
[components.textcat.model.linear_model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = true
length = 262144
ngram_size = 1
no_output_layer = false
{% else -%}
[components.textcat.model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = true
ngram_size = 1
no_output_layer = false
@ -570,15 +573,17 @@ nO = null
width = ${components.tok2vec.model.encode.width}
[components.textcat_multilabel.model.linear_model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = false
length = 262144
ngram_size = 1
no_output_layer = false
{% else -%}
[components.textcat_multilabel.model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = false
length = 262144
ngram_size = 1
no_output_layer = false
{%- endif %}

3
spacy/cli/train.py
View File

@ -47,7 +47,8 @@ def train_cli(
DOCS: https://spacy.io/api/cli#train
"""
util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
if verbose:
util.logger.setLevel(logging.DEBUG)
overrides = parse_config_overrides(ctx.args)
import_code_paths(code_path)
train(config_path, output_path, use_gpu=use_gpu, overrides=overrides)

3
spacy/default_config.cfg
View File

@ -26,6 +26,9 @@ batch_size = 1000
[nlp.tokenizer]
@tokenizers = "spacy.Tokenizer.v1"
[nlp.vectors]
@vectors = "spacy.Vectors.v1"
# The pipeline components and their models
[components]

45
spacy/displacy/render.py
View File

@ -142,7 +142,25 @@ class SpanRenderer:
spans (list): Individual entity spans and their start, end, label, kb_id and kb_url.
title (str / None): Document title set in Doc.user_data['title'].
"""
per_token_info = []
per_token_info = self._assemble_per_token_info(tokens, spans)
markup = self._render_markup(per_token_info)
markup = TPL_SPANS.format(content=markup, dir=self.direction)
if title:
markup = TPL_TITLE.format(title=title) + markup
return markup
@staticmethod
def _assemble_per_token_info(
tokens: List[str], spans: List[Dict[str, Any]]
) -> List[Dict[str, List[Dict[str, Any]]]]:
"""Assembles token info used to generate markup in render_spans().
tokens (List[str]): Tokens in text.
spans (List[Dict[str, Any]]): Spans in text.
RETURNS (List[Dict[str, List[Dict, str, Any]]]): Per token info needed to render HTML markup for given tokens
and spans.
"""
per_token_info: List[Dict[str, List[Dict[str, Any]]]] = []
# we must sort so that we can correctly describe when spans need to "stack"
# which is determined by their start token, then span length (longer spans on top),
# then break any remaining ties with the span label
@ -154,21 +172,22 @@ class SpanRenderer:
s["label"],
),
)
for s in spans:
# this is the vertical 'slot' that the span will be rendered in
# vertical_position = span_label_offset + (offset_step * (slot - 1))
s["render_slot"] = 0
for idx, token in enumerate(tokens):
# Identify if a token belongs to a Span (and which) and if it's a
# start token of said Span. We'll use this for the final HTML render
token_markup: Dict[str, Any] = {}
token_markup["text"] = token
concurrent_spans = 0
intersecting_spans: List[Dict[str, Any]] = []
entities = []
for span in spans:
ent = {}
if span["start_token"] <= idx < span["end_token"]:
concurrent_spans += 1
span_start = idx == span["start_token"]
ent["label"] = span["label"]
ent["is_start"] = span_start
@ -176,7 +195,12 @@ class SpanRenderer:
# When the span starts, we need to know how many other
# spans are on the 'span stack' and will be rendered.
# This value becomes the vertical render slot for this entire span
span["render_slot"] = concurrent_spans
span["render_slot"] = (
intersecting_spans[-1]["render_slot"]
if len(intersecting_spans)
else 0
) + 1
intersecting_spans.append(span)
ent["render_slot"] = span["render_slot"]
kb_id = span.get("kb_id", "")
kb_url = span.get("kb_url", "#")
@ -193,11 +217,8 @@ class SpanRenderer:
span["render_slot"] = 0
token_markup["entities"] = entities
per_token_info.append(token_markup)
markup = self._render_markup(per_token_info)
markup = TPL_SPANS.format(content=markup, dir=self.direction)
if title:
markup = TPL_TITLE.format(title=title) + markup
return markup
return per_token_info
def _render_markup(self, per_token_info: List[Dict[str, Any]]) -> str:
"""Render the markup from per-token information"""
@ -313,6 +334,8 @@ class DependencyRenderer:
self.lang = settings.get("lang", DEFAULT_LANG)
render_id = f"{id_prefix}-{i}"
svg = self.render_svg(render_id, p["words"], p["arcs"])
if p.get("title"):
svg = TPL_TITLE.format(title=p.get("title")) + svg
rendered.append(svg)
if page:
content = "".join([TPL_FIGURE.format(content=svg) for svg in rendered])
@ -565,7 +588,7 @@ class EntityRenderer:
for i, fragment in enumerate(fragments):
markup += escape_html(fragment)
if len(fragments) > 1 and i != len(fragments) - 1:
markup += "</br>"
markup += "<br>"
if self.ents is None or label.upper() in self.ents:
color = self.colors.get(label.upper(), self.default_color)
ent_settings = {
@ -583,7 +606,7 @@ class EntityRenderer:
for i, fragment in enumerate(fragments):
markup += escape_html(fragment)
if len(fragments) > 1 and i != len(fragments) - 1:
markup += "</br>"
markup += "<br>"
markup = TPL_ENTS.format(content=markup, dir=self.direction)
if title:
markup = TPL_TITLE.format(title=title) + markup

12
spacy/errors.py
View File

@ -214,6 +214,7 @@ class Warnings(metaclass=ErrorsWithCodes):
W125 = ("The StaticVectors key_attr is no longer used. To set a custom "
"key attribute for vectors, configure it through Vectors(attr=) or "
"'spacy init vectors --attr'")
W126 = ("These keys are unsupported: {unsupported}")
# v4 warning strings
W401 = ("`incl_prior is True`, but the selected knowledge base type {kb_type} doesn't support prior probability "
@ -226,7 +227,6 @@ class Errors(metaclass=ErrorsWithCodes):
E002 = ("Can't find factory for '{name}' for language {lang} ({lang_code}). "
"This usually happens when spaCy calls `nlp.{method}` with a custom "
"component name that's not registered on the current language class. "
"If you're using a Transformer, make sure to install 'spacy-transformers'. "
"If you're using a custom component, make sure you've added the "
"decorator `@Language.component` (for function components) or "
"`@Language.factory` (for class components).\n\nAvailable "
@ -551,12 +551,12 @@ class Errors(metaclass=ErrorsWithCodes):
"during training, make sure to include it in 'annotating components'")
# New errors added in v3.x
E849 = ("The vocab only supports {method} for vectors of type "
"spacy.vectors.Vectors, not {vectors_type}.")
E850 = ("The PretrainVectors objective currently only supports default or "
"floret vectors, not {mode} vectors.")
E851 = ("The 'textcat' component labels should only have values of 0 or 1, "
"but found value of '{val}'.")
E852 = ("The tar file pulled from the remote attempted an unsafe path "
"traversal.")
E853 = ("Unsupported component factory name '{name}'. The character '.' is "
"not permitted in factory names.")
E854 = ("Unable to set doc.ents. Check that the 'ents_filter' does not "
@ -970,6 +970,12 @@ class Errors(metaclass=ErrorsWithCodes):
" 'min_length': {min_length}, 'max_length': {max_length}")
E1054 = ("The text, including whitespace, must match between reference and "
"predicted docs when training {component}.")
E1055 = ("The 'replace_listener' callback expects {num_params} parameters, "
"but only callbacks with one or three parameters are supported")
E1056 = ("The `TextCatBOW` architecture expects a length of at least 1, was {length}.")
E1057 = ("The `TextCatReduce` architecture must be used with at least one "
"reduction. Please enable one of `use_reduce_first`, "
"`use_reduce_last`, `use_reduce_max` or `use_reduce_mean`.")
# v4 error strings
E4000 = ("Expected a Doc as input, but got: '{type}'")

7
spacy/kb/__init__.py
View File

@ -2,4 +2,9 @@ from .candidate import Candidate, InMemoryCandidate
from .kb import KnowledgeBase
from .kb_in_memory import InMemoryLookupKB
__all__ = ["KnowledgeBase", "InMemoryLookupKB", "Candidate", "InMemoryCandidate"]
__all__ = [
"Candidate",
"KnowledgeBase",
"InMemoryCandidate",
"InMemoryLookupKB",
]

2
spacy/kb/candidate.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True
# cython: infer_types=True
from .kb_in_memory cimport InMemoryLookupKB

2
spacy/kb/kb.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True
# cython: infer_types=True
from pathlib import Path
from typing import Iterable, Tuple, Union

2
spacy/kb/kb_in_memory.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True
# cython: infer_types=True
from typing import Any, Callable, Dict, Iterable
import srsly

6
spacy/lang/en/lex_attrs.py
View File

@ -6,7 +6,8 @@ _num_words = [
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
"sixteen", "seventeen", "eighteen", "nineteen", "twenty", "thirty", "forty",
"fifty", "sixty", "seventy", "eighty", "ninety", "hundred", "thousand",
"million", "billion", "trillion", "quadrillion", "gajillion", "bazillion"
"million", "billion", "trillion", "quadrillion", "quintillion", "sextillion",
"septillion", "octillion", "nonillion", "decillion", "gajillion", "bazillion"
]
_ordinal_words = [
"first", "second", "third", "fourth", "fifth", "sixth", "seventh", "eighth",
@ -14,7 +15,8 @@ _ordinal_words = [
"fifteenth", "sixteenth", "seventeenth", "eighteenth", "nineteenth",
"twentieth", "thirtieth", "fortieth", "fiftieth", "sixtieth", "seventieth",
"eightieth", "ninetieth", "hundredth", "thousandth", "millionth", "billionth",
"trillionth", "quadrillionth", "gajillionth", "bazillionth"
"trillionth", "quadrillionth", "quintillionth", "sextillionth", "septillionth",
"octillionth", "nonillionth", "decillionth", "gajillionth", "bazillionth"
]
# fmt: on

4
spacy/lang/es/lemmatizer.py
View File

@ -163,7 +163,7 @@ class SpanishLemmatizer(Lemmatizer):
for old, new in self.lookups.get_table("lemma_rules").get("det", []):
if word == old:
return [new]
# If none of the specfic rules apply, search in the common rules for
# If none of the specific rules apply, search in the common rules for
# determiners and pronouns that follow a unique pattern for
# lemmatization. If the word is in the list, return the corresponding
# lemma.
@ -291,7 +291,7 @@ class SpanishLemmatizer(Lemmatizer):
for old, new in self.lookups.get_table("lemma_rules").get("pron", []):
if word == old:
return [new]
# If none of the specfic rules apply, search in the common rules for
# If none of the specific rules apply, search in the common rules for
# determiners and pronouns that follow a unique pattern for
# lemmatization. If the word is in the list, return the corresponding
# lemma.

18
spacy/lang/fo/__init__.py Normal file
View File

@ -0,0 +1,18 @@
from ...language import BaseDefaults, Language
from ..punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class FaroeseDefaults(BaseDefaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
prefixes = TOKENIZER_PREFIXES
class Faroese(Language):
lang = "fo"
Defaults = FaroeseDefaults
__all__ = ["Faroese"]

90
spacy/lang/fo/tokenizer_exceptions.py Normal file
View File

@ -0,0 +1,90 @@
from ...symbols import ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}
for orth in [
"apr.",
"aug.",
"avgr.",
"árg.",
"ávís.",
"beinl.",
"blkv.",
"blaðkv.",
"blm.",
"blaðm.",
"bls.",
"blstj.",
"blaðstj.",
"des.",
"eint.",
"febr.",
"fyrrv.",
"góðk.",
"h.m.",
"innt.",
"jan.",
"kl.",
"m.a.",
"mðr.",
"mió.",
"nr.",
"nto.",
"nov.",
"nút.",
"o.a.",
"o.a.m.",
"o.a.tíl.",
"o.fl.",
"ff.",
"o.m.a.",
"o.o.",
"o.s.fr.",
"o.tíl.",
"o.ø.",
"okt.",
"omf.",
"pst.",
"ritstj.",
"sbr.",
"sms.",
"smst.",
"smb.",
"sb.",
"sbrt.",
"sp.",
"sept.",
"spf.",
"spsk.",
"t.e.",
"t.s.",
"t.s.s.",
"tlf.",
"tel.",
"tsk.",
"t.o.v.",
"t.d.",
"uml.",
"ums.",
"uppl.",
"upprfr.",
"uppr.",
"útg.",
"útl.",
"útr.",
"vanl.",
"v.",
"v.h.",
"v.ø.o.",
"viðm.",
"viðv.",
"vm.",
"v.m.",
]:
_exc[orth] = [{ORTH: orth}]
capitalized = orth.capitalize()
_exc[capitalized] = [{ORTH: capitalized}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)

2
spacy/lang/grc/punctuation.py
View File

@ -15,6 +15,7 @@ _prefixes = (
[
"†",
"⸏",
"〈",
]
+ LIST_PUNCT
+ LIST_ELLIPSES
@ -31,6 +32,7 @@ _suffixes = (
+ [
"†",
"⸎",
"〉",
r"(?<=[\u1F00-\u1FFF\u0370-\u03FF])[\-\.⸏]",
]
)

20
spacy/lang/nn/__init__.py Normal file
View File

@ -0,0 +1,20 @@
from ...language import BaseDefaults, Language
from ..nb import SYNTAX_ITERATORS
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class NorwegianNynorskDefaults(BaseDefaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
prefixes = TOKENIZER_PREFIXES
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
syntax_iterators = SYNTAX_ITERATORS
class NorwegianNynorsk(Language):
lang = "nn"
Defaults = NorwegianNynorskDefaults
__all__ = ["NorwegianNynorsk"]

15
spacy/lang/nn/examples.py Normal file
View File

@ -0,0 +1,15 @@
"""
Example sentences to test spaCy and its language models.
>>> from spacy.lang.nn.examples import sentences
>>> docs = nlp.pipe(sentences)
"""
# sentences taken from Omsetjingsminne frå Nynorsk pressekontor 2022 (https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-80/)
sentences = [
"Konseptet går ut på at alle tre omgangar tel, alle hopparar må stille i kvalifiseringa og poengsummen skal telje.",
"Det er ein meir enn i same periode i fjor.",
"Det har lava ned enorme snømengder i store delar av Europa den siste tida.",
"Akhtar Chaudhry er ikkje innstilt på Oslo-lista til SV, men utfordrar Heikki Holmås om førsteplassen.",
]

74
spacy/lang/nn/punctuation.py Normal file
View File

@ -0,0 +1,74 @@
from ..char_classes import (
ALPHA,
ALPHA_LOWER,
ALPHA_UPPER,
CONCAT_QUOTES,
CURRENCY,
LIST_CURRENCY,
LIST_ELLIPSES,
LIST_ICONS,
LIST_PUNCT,
LIST_QUOTES,
PUNCT,
UNITS,
)
from ..punctuation import TOKENIZER_SUFFIXES
_quotes = CONCAT_QUOTES.replace("'", "")
_list_punct = [x for x in LIST_PUNCT if x != "#"]
_list_icons = [x for x in LIST_ICONS if x != "°"]
_list_icons = [x.replace("\\u00B0", "") for x in _list_icons]
_list_quotes = [x for x in LIST_QUOTES if x != "\\'"]
_prefixes = (
["§", "%", "=", "—", "–", r"\+(?![0-9])"]
+ _list_punct
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_CURRENCY
+ LIST_ICONS
)
_infixes = (
LIST_ELLIPSES
+ _list_icons
+ [
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])[:<>=/](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
]
)
_suffixes = (
LIST_PUNCT
+ LIST_ELLIPSES
+ _list_quotes
+ _list_icons
+ ["—", "–"]
+ [
r"(?<=[0-9])\+",
r"(?<=°[FfCcKk])\.",
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
r"(?<=[0-9])(?:{u})".format(u=UNITS),
r"(?<=[{al}{e}{p}(?:{q})])\.".format(
al=ALPHA_LOWER, e=r"%²\-\+", q=_quotes, p=PUNCT
),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
]
+ [r"(?<=[^sSxXzZ])'"]
)
_suffixes += [
suffix
for suffix in TOKENIZER_SUFFIXES
if suffix not in ["'s", "'S", "’s", "’S", r"\'"]
]
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_INFIXES = _infixes
TOKENIZER_SUFFIXES = _suffixes

228
spacy/lang/nn/tokenizer_exceptions.py Normal file
View File

@ -0,0 +1,228 @@
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}
for exc_data in [
{ORTH: "jan.", NORM: "januar"},
{ORTH: "feb.", NORM: "februar"},
{ORTH: "mar.", NORM: "mars"},
{ORTH: "apr.", NORM: "april"},
{ORTH: "jun.", NORM: "juni"},
# note: "jul." is in the simple list below without a NORM exception
{ORTH: "aug.", NORM: "august"},
{ORTH: "sep.", NORM: "september"},
{ORTH: "okt.", NORM: "oktober"},
{ORTH: "nov.", NORM: "november"},
{ORTH: "des.", NORM: "desember"},
]:
_exc[exc_data[ORTH]] = [exc_data]
for orth in [
"Ap.",
"Aq.",
"Ca.",
"Chr.",
"Co.",
"Dr.",
"F.eks.",
"Fr.p.",
"Frp.",
"Grl.",
"Kr.",
"Kr.F.",
"Kr.F.s",
"Mr.",
"Mrs.",
"Pb.",
"Pr.",
"Sp.",
"St.",
"a.m.",
"ad.",
"adm.dir.",
"adr.",
"b.c.",
"bl.a.",
"bla.",
"bm.",
"bnr.",
"bto.",
"c.c.",
"ca.",
"cand.mag.",
"co.",
"d.d.",
"d.m.",
"d.y.",
"dept.",
"dr.",
"dr.med.",
"dr.philos.",
"dr.psychol.",
"dss.",
"dvs.",
"e.Kr.",
"e.l.",
"eg.",
"eig.",
"ekskl.",
"el.",
"et.",
"etc.",
"etg.",
"ev.",
"evt.",
"f.",
"f.Kr.",
"f.eks.",
"f.o.m.",
"fhv.",
"fk.",
"foreg.",
"fork.",
"fv.",
"fvt.",
"g.",
"gl.",
"gno.",
"gnr.",
"grl.",
"gt.",
"h.r.adv.",
"hhv.",
"hoh.",
"hr.",
"ifb.",
"ifm.",
"iht.",
"inkl.",
"istf.",
"jf.",
"jr.",
"jul.",
"juris.",
"kfr.",
"kgl.",
"kgl.res.",
"kl.",
"komm.",
"kr.",
"kst.",
"lat.",
"lø.",
"m.a.",
"m.a.o.",
"m.fl.",
"m.m.",
"m.v.",
"ma.",
"mag.art.",
"md.",
"mfl.",
"mht.",
"mill.",
"min.",
"mnd.",
"moh.",
"mrd.",
"muh.",
"mv.",
"mva.",
"n.å.",
"ndf.",
"nr.",
"nto.",
"nyno.",
"o.a.",
"o.l.",
"obl.",
"off.",
"ofl.",
"on.",
"op.",
"org.",
"osv.",
"ovf.",
"p.",
"p.a.",
"p.g.a.",
"p.m.",
"p.t.",
"pga.",
"ph.d.",
"pkt.",
"pr.",
"pst.",
"pt.",
"red.anm.",
"ref.",
"res.",
"res.kap.",
"resp.",
"rv.",
"s.",
"s.d.",
"s.k.",
"s.u.",
"s.å.",
"sen.",
"sep.",
"siviling.",
"sms.",
"snr.",
"spm.",
"sr.",
"sst.",
"st.",
"st.meld.",
"st.prp.",
"stip.",
"stk.",
"stud.",
"sv.",
"såk.",
"sø.",
"t.d.",
"t.h.",
"t.o.m.",
"t.v.",
"temp.",
"ti.",
"tils.",
"tilsv.",
"tl;dr",
"tlf.",
"to.",
"ult.",
"utg.",
"v.",
"vedk.",
"vedr.",
"vg.",
"vgs.",
"vha.",
"vit.ass.",
"vn.",
"vol.",
"vs.",
"vsa.",
"§§",
"©NTB",
"årg.",
"årh.",
]:
_exc[orth] = [{ORTH: orth}]
# Dates
for h in range(1, 31 + 1):
for period in ["."]:
_exc[f"{h}{period}"] = [{ORTH: f"{h}."}]
_custom_base_exc = {"i.": [{ORTH: "i", NORM: "i"}, {ORTH: "."}]}
_exc.update(_custom_base_exc)
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)

3
spacy/lang/tr/examples.py
View File

@ -15,4 +15,7 @@ sentences = [
"Türkiye'nin başkenti neresi?",
"Bakanlar Kurulu 180 günlük eylem planını açıkladı.",
"Merkez Bankası, beklentiler doğrultusunda faizlerde değişikliğe gitmedi.",
"Cemal Sureya kimdir?",
"Bunlari Biliyor muydunuz?",
"Altinoluk Turkiye haritasinin neresinde yer alir?",
]

35
spacy/language.py
View File

@ -1,4 +1,5 @@
import functools
import inspect
import itertools
import multiprocessing as mp
import random
@ -64,6 +65,7 @@ from .util import (
registry,
warn_if_jupyter_cupy,
)
from .vectors import BaseVectors
from .vocab import Vocab, create_vocab
PipeCallable = Callable[[Doc], Doc]
@ -153,6 +155,7 @@ class Language:
max_length: int = 10**6,
meta: Dict[str, Any] = {},
create_tokenizer: Optional[Callable[["Language"], Callable[[str], Doc]]] = None,
create_vectors: Optional[Callable[["Vocab"], BaseVectors]] = None,
batch_size: int = 1000,
**kwargs,
) -> None:
@ -192,6 +195,10 @@ class Language:
raise ValueError(Errors.E918.format(vocab=vocab, vocab_type=type(Vocab)))
if vocab is True:
vocab = create_vocab(self.lang, self.Defaults)
if not create_vectors:
vectors_cfg = {"vectors": self._config["nlp"]["vectors"]}
create_vectors = registry.resolve(vectors_cfg)["vectors"]
vocab.vectors = create_vectors(vocab)
else:
if (self.lang and vocab.lang) and (self.lang != vocab.lang):
raise ValueError(Errors.E150.format(nlp=self.lang, vocab=vocab.lang))
@ -1878,6 +1885,10 @@ class Language:
).merge(config)
if "nlp" not in config:
raise ValueError(Errors.E985.format(config=config))
# fill in [nlp.vectors] if not present (as a narrower alternative to
# auto-filling [nlp] from the default config)
if "vectors" not in config["nlp"]:
config["nlp"]["vectors"] = {"@vectors": "spacy.Vectors.v1"}
config_lang = config["nlp"].get("lang")
if config_lang is not None and config_lang != cls.lang:
raise ValueError(
@ -1913,6 +1924,7 @@ class Language:
filled["nlp"], validate=validate, schema=ConfigSchemaNlp
)
create_tokenizer = resolved_nlp["tokenizer"]
create_vectors = resolved_nlp["vectors"]
before_creation = resolved_nlp["before_creation"]
after_creation = resolved_nlp["after_creation"]
after_pipeline_creation = resolved_nlp["after_pipeline_creation"]
@ -1933,7 +1945,12 @@ class Language:
# inside stuff like the spacy train function. If we loaded them here,
# then we would load them twice at runtime: once when we make from config,
# and then again when we load from disk.
nlp = lang_cls(vocab=vocab, create_tokenizer=create_tokenizer, meta=meta)
nlp = lang_cls(
vocab=vocab,
create_tokenizer=create_tokenizer,
create_vectors=create_vectors,
meta=meta,
)
if after_creation is not None:
nlp = after_creation(nlp)
if not isinstance(nlp, cls):
@ -2150,8 +2167,20 @@ class Language:
# Go over the listener layers and replace them
for listener in pipe_listeners:
new_model = tok2vec_model.copy()
if "replace_listener" in tok2vec_model.attrs:
new_model = tok2vec_model.attrs["replace_listener"](new_model)
replace_listener_func = tok2vec_model.attrs.get("replace_listener")
if replace_listener_func is not None:
# Pass the extra args to the callback without breaking compatibility with
# old library versions that only expect a single parameter.
num_params = len(
inspect.signature(replace_listener_func).parameters
)
if num_params == 1:
new_model = replace_listener_func(new_model)
elif num_params == 3:
new_model = replace_listener_func(new_model, listener, tok2vec)
else:
raise ValueError(Errors.E1055.format(num_params=num_params))
util.replace_model_node(pipe.model, listener, new_model) # type: ignore[attr-defined]
tok2vec.remove_listener(listener, pipe_name)

1
spacy/lexeme.pyx
View File

@ -1,4 +1,5 @@
# cython: embedsignature=True
# cython: profile=False
# Compiler crashes on memory view coercion without this. Should report bug.
cimport numpy as np
from libc.string cimport memset

2
spacy/matcher/__init__.py
View File

@ -3,4 +3,4 @@ from .levenshtein import levenshtein
from .matcher import Matcher
from .phrasematcher import PhraseMatcher
__all__ = ["Matcher", "PhraseMatcher", "DependencyMatcher", "levenshtein"]
__all__ = ["DependencyMatcher", "Matcher", "PhraseMatcher", "levenshtein"]

10
spacy/matcher/dependencymatcher.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True
# cython: infer_types=True
import warnings
from collections import defaultdict
from itertools import product
@ -129,6 +129,7 @@ cdef class DependencyMatcher:
else:
required_keys = {"RIGHT_ID", "RIGHT_ATTRS", "REL_OP", "LEFT_ID"}
relation_keys = set(relation.keys())
# Identify required keys that have not been specified
missing = required_keys - relation_keys
if missing:
missing_txt = ", ".join(list(missing))
@ -136,6 +137,13 @@ cdef class DependencyMatcher:
required=required_keys,
missing=missing_txt
))
# Identify additional, unsupported keys
unsupported = relation_keys - required_keys
if unsupported:
unsupported_txt = ", ".join(list(unsupported))
warnings.warn(Warnings.W126.format(
unsupported=unsupported_txt
))
if (
relation["RIGHT_ID"] in visited_nodes
or relation["LEFT_ID"] not in visited_nodes

2
spacy/matcher/levenshtein.pyx
View File

@ -1,4 +1,4 @@
# cython: profile=True, binding=True, infer_types=True
# cython: binding=True, infer_types=True
from cpython.object cimport PyObject
from libc.stdint cimport int64_t

2
spacy/matcher/matcher.pyx
View File

@ -1,4 +1,4 @@
# cython: binding=True, infer_types=True, profile=True
# cython: binding=True, infer_types=True
from typing import Iterable, List
from cymem.cymem cimport Pool

2
spacy/matcher/phrasematcher.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True
# cython: infer_types=True
from collections import defaultdict
from typing import List

238
spacy/ml/models/textcat.py
View File

@ -1,21 +1,27 @@
from functools import partial
from typing import List, Optional, cast
from typing import List, Optional, Tuple, cast
from thinc.api import (
Dropout,
Gelu,
LayerNorm,
Linear,
Logistic,
Maxout,
Model,
ParametricAttention,
ParametricAttention_v2,
Relu,
Softmax,
SparseLinear,
SparseLinear_v2,
chain,
clone,
concatenate,
list2ragged,
reduce_first,
reduce_last,
reduce_max,
reduce_mean,
reduce_sum,
residual,
@ -25,9 +31,10 @@ from thinc.api import (
)
from thinc.layers.chain import init as init_chain
from thinc.layers.resizable import resize_linear_weighted, resize_model
from thinc.types import Floats2d
from thinc.types import ArrayXd, Floats2d
from ...attrs import ORTH
from ...errors import Errors
from ...tokens import Doc
from ...util import registry
from ..extract_ngrams import extract_ngrams
@ -47,39 +54,15 @@ def build_simple_cnn_text_classifier(
outputs sum to 1. If exclusive_classes=False, a logistic non-linearity
is applied instead, so that outputs are in the range [0, 1].
"""
fill_defaults = {"b": 0, "W": 0}
with Model.define_operators({">>": chain}):
cnn = tok2vec >> list2ragged() >> reduce_mean()
nI = tok2vec.maybe_get_dim("nO")
if exclusive_classes:
output_layer = Softmax(nO=nO, nI=nI)
fill_defaults["b"] = NEG_VALUE
resizable_layer: Model = resizable(
output_layer,
resize_layer=partial(
resize_linear_weighted, fill_defaults=fill_defaults
),
)
model = cnn >> resizable_layer
else:
output_layer = Linear(nO=nO, nI=nI)
resizable_layer = resizable(
output_layer,
resize_layer=partial(
resize_linear_weighted, fill_defaults=fill_defaults
),
)
model = cnn >> resizable_layer >> Logistic()
model.set_ref("output_layer", output_layer)
model.attrs["resize_output"] = partial(
resize_and_set_ref,
resizable_layer=resizable_layer,
)
model.set_ref("tok2vec", tok2vec)
if nO is not None:
model.set_dim("nO", cast(int, nO))
model.attrs["multi_label"] = not exclusive_classes
return model
return build_reduce_text_classifier(
tok2vec=tok2vec,
exclusive_classes=exclusive_classes,
use_reduce_first=False,
use_reduce_last=False,
use_reduce_max=False,
use_reduce_mean=True,
nO=nO,
)
def resize_and_set_ref(model, new_nO, resizable_layer):
@ -95,10 +78,48 @@ def build_bow_text_classifier(
ngram_size: int,
no_output_layer: bool,
nO: Optional[int] = None,
) -> Model[List[Doc], Floats2d]:
return _build_bow_text_classifier(
exclusive_classes=exclusive_classes,
ngram_size=ngram_size,
no_output_layer=no_output_layer,
nO=nO,
sparse_linear=SparseLinear(nO=nO),
)
@registry.architectures("spacy.TextCatBOW.v3")
def build_bow_text_classifier_v3(
exclusive_classes: bool,
ngram_size: int,
no_output_layer: bool,
length: int = 262144,
nO: Optional[int] = None,
) -> Model[List[Doc], Floats2d]:
if length < 1:
raise ValueError(Errors.E1056.format(length=length))
# Find k such that 2**(k-1) < length <= 2**k.
length = 2 ** (length - 1).bit_length()
return _build_bow_text_classifier(
exclusive_classes=exclusive_classes,
ngram_size=ngram_size,
no_output_layer=no_output_layer,
nO=nO,
sparse_linear=SparseLinear_v2(nO=nO, length=length),
)
def _build_bow_text_classifier(
exclusive_classes: bool,
ngram_size: int,
no_output_layer: bool,
sparse_linear: Model[Tuple[ArrayXd, ArrayXd, ArrayXd], ArrayXd],
nO: Optional[int] = None,
) -> Model[List[Doc], Floats2d]:
fill_defaults = {"b": 0, "W": 0}
with Model.define_operators({">>": chain}):
sparse_linear = SparseLinear(nO=nO)
output_layer = None
if not no_output_layer:
fill_defaults["b"] = NEG_VALUE
@ -127,6 +148,9 @@ def build_text_classifier_v2(
linear_model: Model[List[Doc], Floats2d],
nO: Optional[int] = None,
) -> Model[List[Doc], Floats2d]:
# TODO: build the model with _build_parametric_attention_with_residual_nonlinear
# in spaCy v4. We don't do this in spaCy v3 to preserve model
# compatibility.
exclusive_classes = not linear_model.attrs["multi_label"]
with Model.define_operators({">>": chain, "|": concatenate}):
width = tok2vec.maybe_get_dim("nO")
@ -190,3 +214,145 @@ def build_text_classifier_lowdata(
model = model >> Dropout(dropout)
model = model >> Logistic()
return model
@registry.architectures("spacy.TextCatParametricAttention.v1")
def build_textcat_parametric_attention_v1(
tok2vec: Model[List[Doc], List[Floats2d]],
exclusive_classes: bool,
nO: Optional[int] = None,
) -> Model[List[Doc], Floats2d]:
width = tok2vec.maybe_get_dim("nO")
parametric_attention = _build_parametric_attention_with_residual_nonlinear(
tok2vec=tok2vec,
nonlinear_layer=Maxout(nI=width, nO=width),
key_transform=Gelu(nI=width, nO=width),
)
with Model.define_operators({">>": chain}):
if exclusive_classes:
output_layer = Softmax(nO=nO)
else:
output_layer = Linear(nO=nO) >> Logistic()
model = parametric_attention >> output_layer
if model.has_dim("nO") is not False and nO is not None:
model.set_dim("nO", cast(int, nO))
model.set_ref("output_layer", output_layer)
model.attrs["multi_label"] = not exclusive_classes
return model
def _build_parametric_attention_with_residual_nonlinear(
*,
tok2vec: Model[List[Doc], List[Floats2d]],
nonlinear_layer: Model[Floats2d, Floats2d],
key_transform: Optional[Model[Floats2d, Floats2d]] = None,
) -> Model[List[Doc], Floats2d]:
with Model.define_operators({">>": chain, "|": concatenate}):
width = tok2vec.maybe_get_dim("nO")
attention_layer = ParametricAttention_v2(nO=width, key_transform=key_transform)
norm_layer = LayerNorm(nI=width)
parametric_attention = (
tok2vec
>> list2ragged()
>> attention_layer
>> reduce_sum()
>> residual(nonlinear_layer >> norm_layer >> Dropout(0.0))
)
parametric_attention.init = _init_parametric_attention_with_residual_nonlinear
parametric_attention.set_ref("tok2vec", tok2vec)
parametric_attention.set_ref("attention_layer", attention_layer)
parametric_attention.set_ref("nonlinear_layer", nonlinear_layer)
parametric_attention.set_ref("norm_layer", norm_layer)
return parametric_attention
def _init_parametric_attention_with_residual_nonlinear(model, X, Y) -> Model:
tok2vec_width = get_tok2vec_width(model)
model.get_ref("attention_layer").set_dim("nO", tok2vec_width)
model.get_ref("nonlinear_layer").set_dim("nO", tok2vec_width)
model.get_ref("nonlinear_layer").set_dim("nI", tok2vec_width)
model.get_ref("norm_layer").set_dim("nI", tok2vec_width)
model.get_ref("norm_layer").set_dim("nO", tok2vec_width)
init_chain(model, X, Y)
return model
@registry.architectures("spacy.TextCatReduce.v1")
def build_reduce_text_classifier(
tok2vec: Model,
exclusive_classes: bool,
use_reduce_first: bool,
use_reduce_last: bool,
use_reduce_max: bool,
use_reduce_mean: bool,
nO: Optional[int] = None,
) -> Model[List[Doc], Floats2d]:
"""Build a model that classifies pooled `Doc` representations.
Pooling is performed using reductions. Reductions are concatenated when
multiple reductions are used.
tok2vec (Model): the tok2vec layer to pool over.
exclusive_classes (bool): Whether or not classes are mutually exclusive.
use_reduce_first (bool): Pool by using the hidden representation of the
first token of a `Doc`.
use_reduce_last (bool): Pool by using the hidden representation of the
last token of a `Doc`.
use_reduce_max (bool): Pool by taking the maximum values of the hidden
representations of a `Doc`.
use_reduce_mean (bool): Pool by taking the mean of all hidden
representations of a `Doc`.
nO (Optional[int]): Number of classes.
"""
fill_defaults = {"b": 0, "W": 0}
reductions = []
if use_reduce_first:
reductions.append(reduce_first())
if use_reduce_last:
reductions.append(reduce_last())
if use_reduce_max:
reductions.append(reduce_max())
if use_reduce_mean:
reductions.append(reduce_mean())
if not len(reductions):
raise ValueError(Errors.E1057)
with Model.define_operators({">>": chain}):
cnn = tok2vec >> list2ragged() >> concatenate(*reductions)
nO_tok2vec = tok2vec.maybe_get_dim("nO")
nI = nO_tok2vec * len(reductions) if nO_tok2vec is not None else None
if exclusive_classes:
output_layer = Softmax(nO=nO, nI=nI)
fill_defaults["b"] = NEG_VALUE
resizable_layer: Model = resizable(
output_layer,
resize_layer=partial(
resize_linear_weighted, fill_defaults=fill_defaults
),
)
model = cnn >> resizable_layer
else:
output_layer = Linear(nO=nO, nI=nI)
resizable_layer = resizable(
output_layer,
resize_layer=partial(
resize_linear_weighted, fill_defaults=fill_defaults
),
)
model = cnn >> resizable_layer >> Logistic()
model.set_ref("output_layer", output_layer)
model.attrs["resize_output"] = partial(
resize_and_set_ref,
resizable_layer=resizable_layer,
)
model.set_ref("tok2vec", tok2vec)
if nO is not None:
model.set_dim("nO", cast(int, nO))
model.attrs["multi_label"] = not exclusive_classes
return model

4
spacy/ml/models/tok2vec.py
View File

@ -67,8 +67,8 @@ def build_hash_embed_cnn_tok2vec(
are between 2 and 8.
window_size (int): The number of tokens on either side to concatenate during
the convolutions. The receptive field of the CNN will be
depth * (window_size * 2 + 1), so a 4-layer network with window_size of
2 will be sensitive to 20 words at a time. Recommended value is 1.
depth * window_size * 2 + 1, so a 4-layer network with window_size of
2 will be sensitive to 17 words at a time. Recommended value is 1.
embed_size (int): The number of rows in the hash embedding tables. This can
be surprisingly small, due to the use of the hash embeddings. Recommended
values are between 2000 and 10000.

1
spacy/ml/parser_model.pyx
View File

@ -1,4 +1,5 @@
# cython: infer_types=True, cdivision=True, boundscheck=False
# cython: profile=False
cimport numpy as np
from libc.math cimport exp
from libc.stdlib cimport calloc, free, realloc

11
spacy/ml/staticvectors.py
View File

@ -9,7 +9,7 @@ from thinc.util import partial
from ..attrs import ORTH
from ..errors import Errors, Warnings
from ..tokens import Doc
from ..vectors import Mode
from ..vectors import Mode, Vectors
from ..vocab import Vocab
@ -48,11 +48,14 @@ def forward(
key_attr: int = getattr(vocab.vectors, "attr", ORTH)
keys = model.ops.flatten([cast(Ints1d, doc.to_array(key_attr)) for doc in docs])
W = cast(Floats2d, model.ops.as_contig(model.get_param("W")))
if vocab.vectors.mode == Mode.default:
if isinstance(vocab.vectors, Vectors) and vocab.vectors.mode == Mode.default:
V = model.ops.asarray(vocab.vectors.data)
rows = vocab.vectors.find(keys=keys)
V = model.ops.as_contig(V[rows])
elif vocab.vectors.mode == Mode.floret:
elif isinstance(vocab.vectors, Vectors) and vocab.vectors.mode == Mode.floret:
V = vocab.vectors.get_batch(keys)
V = model.ops.as_contig(V)
elif hasattr(vocab.vectors, "get_batch"):
V = vocab.vectors.get_batch(keys)
V = model.ops.as_contig(V)
else:
@ -61,7 +64,7 @@ def forward(
vectors_data = model.ops.gemm(V, W, trans2=True)
except ValueError:
raise RuntimeError(Errors.E896)
if vocab.vectors.mode == Mode.default:
if isinstance(vocab.vectors, Vectors) and vocab.vectors.mode == Mode.default:
# Convert negative indices to 0-vectors
# TODO: more options for UNK tokens
vectors_data[rows < 0] = 0

1
spacy/morphology.pyx
View File

@ -1,4 +1,5 @@
# cython: infer_types
# cython: profile=False
import warnings
from typing import Dict, List, Optional, Tuple, Union

2
spacy/parts_of_speech.pyx
View File

@ -1,4 +1,4 @@
# cython: profile=False
IDS = {
"": NO_TAG,
"ADJ": ADJ,

1
spacy/pipeline/__init__.py
View File

@ -21,6 +21,7 @@ from .trainable_pipe import TrainablePipe
__all__ = [
"AttributeRuler",
"DependencyParser",
"EditTreeLemmatizer",
"EntityLinker",
"EntityRecognizer",
"Morphologizer",

1
spacy/pipeline/_edit_tree_internals/edit_trees.pyx
View File

@ -1,4 +1,5 @@
# cython: infer_types=True, binding=True
# cython: profile=False
from cython.operator cimport dereference as deref
from libc.stdint cimport UINT32_MAX, uint32_t
from libc.string cimport memset

8
spacy/pipeline/_edit_tree_internals/schemas.py
View File

@ -1,8 +1,12 @@
from collections import defaultdict
from typing import Any, Dict, List, Union
from pydantic import BaseModel, Field, ValidationError
from pydantic.types import StrictBool, StrictInt, StrictStr
try:
from pydantic.v1 import BaseModel, Field, ValidationError
from pydantic.v1.types import StrictBool, StrictInt, StrictStr
except ImportError:
from pydantic import BaseModel, Field, ValidationError # type: ignore
from pydantic.types import StrictBool, StrictInt, StrictStr # type: ignore
class MatchNodeSchema(BaseModel):

1
spacy/pipeline/_parser_internals/_beam_utils.pyx
View File

@ -1,5 +1,4 @@
# cython: infer_types=True
# cython: profile=True
import numpy
from ...typedefs cimport class_t

1
spacy/pipeline/_parser_internals/_state.pyx
View File

@ -0,0 +1 @@
# cython: profile=False

2
spacy/pipeline/_parser_internals/arc_eager.pyx
View File

@ -1,4 +1,4 @@
# cython: profile=True, cdivision=True, infer_types=True
# cython: cdivision=True, infer_types=True
from cymem.cymem cimport Address, Pool
from libc.stdint cimport int32_t
from libcpp.vector cimport vector

1
spacy/pipeline/_parser_internals/ner.pyx
View File

@ -1,3 +1,4 @@
# cython: profile=False
from cymem.cymem cimport Pool
from libcpp.memory cimport shared_ptr
from libcpp.vector cimport vector

2
spacy/pipeline/_parser_internals/nonproj.pyx
View File

@ -1,4 +1,4 @@
# cython: profile=True, infer_types=True
# cython: infer_types=True
"""Implements the projectivize/deprojectivize mechanism in Nivre & Nilsson 2005
for doing pseudo-projective parsing implementation uses the HEAD decoration
scheme.

1
spacy/pipeline/_parser_internals/stateclass.pyx
View File

@ -1,4 +1,5 @@
# cython: infer_types=True
# cython: profile=False
from libcpp.vector cimport vector
from ...tokens.doc cimport Doc

1
spacy/pipeline/_parser_internals/transition_system.pyx
View File

@ -1,4 +1,5 @@
# cython: infer_types=True
# cython: profile=False
from __future__ import print_function
from cymem.cymem cimport Pool

2
spacy/pipeline/dep_parser.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True, binding=True
# cython: infer_types=True, binding=True
from collections import defaultdict
from typing import Callable, Optional

2
spacy/pipeline/morphologizer.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True, binding=True
# cython: infer_types=True, binding=True
from itertools import islice
from typing import Callable, Dict, Iterable, Optional, Union

2
spacy/pipeline/ner.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True, binding=True
# cython: infer_types=True, binding=True
from collections import defaultdict
from typing import Callable, Optional

2
spacy/pipeline/pipe.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True, binding=True
# cython: infer_types=True, binding=True
from typing import Callable, Dict, Iterable, Iterator, Tuple, Union
import srsly

2
spacy/pipeline/sentencizer.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True, binding=True
# cython: infer_types=True, binding=True
from typing import Callable, List, Optional
import srsly

2
spacy/pipeline/senter.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True, binding=True
# cython: infer_types=True, binding=True
from itertools import islice
from typing import Callable, Iterable, Optional

2
spacy/pipeline/tagger.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True, binding=True
# cython: infer_types=True, binding=True
from itertools import islice
from typing import Callable, Dict, Iterable, List, Optional, Tuple, Union

12
spacy/pipeline/textcat.py
View File

@ -39,8 +39,9 @@ maxout_pieces = 3
depth = 2
[model.linear_model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = true
length = 262144
ngram_size = 1
no_output_layer = false
"""
@ -48,16 +49,21 @@ DEFAULT_SINGLE_TEXTCAT_MODEL = Config().from_str(single_label_default_config)["m
single_label_bow_config = """
[model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = true
length = 262144
ngram_size = 1
no_output_layer = false
"""
single_label_cnn_config = """
[model]
@architectures = "spacy.TextCatCNN.v2"
@architectures = "spacy.TextCatReduce.v1"
exclusive_classes = true
use_reduce_first = false
use_reduce_last = false
use_reduce_max = false
use_reduce_mean = true
[model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v2"

11
spacy/pipeline/textcat_multilabel.py
View File

@ -35,8 +35,9 @@ maxout_pieces = 3
depth = 2
[model.linear_model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = false
length = 262144
ngram_size = 1
no_output_layer = false
"""
@ -44,7 +45,7 @@ DEFAULT_MULTI_TEXTCAT_MODEL = Config().from_str(multi_label_default_config)["mod
multi_label_bow_config = """
[model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = false
ngram_size = 1
no_output_layer = false
@ -52,8 +53,12 @@ no_output_layer = false
multi_label_cnn_config = """
[model]
@architectures = "spacy.TextCatCNN.v2"
@architectures = "spacy.TextCatReduce.v1"
exclusive_classes = false
use_reduce_first = false
use_reduce_last = false
use_reduce_max = false
use_reduce_mean = true
[model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v2"

2
spacy/pipeline/trainable_pipe.pyx
View File

@ -1,4 +1,4 @@
# cython: infer_types=True, profile=True, binding=True
# cython: infer_types=True, binding=True
from typing import Callable, Dict, Iterable, Iterator, Optional, Tuple
import srsly

1
spacy/pipeline/transition_parser.pyx
View File

@ -1,4 +1,5 @@
# cython: infer_types=True, cdivision=True, boundscheck=False, binding=True
# cython: profile=False
from __future__ import print_function
from typing import Dict, Iterable, List, Optional, Tuple

102
spacy/schemas.py
View File

@ -17,19 +17,34 @@ from typing import (
Union,
)
from pydantic import (
BaseModel,
ConstrainedStr,
Field,
StrictBool,
StrictFloat,
StrictInt,
StrictStr,
ValidationError,
create_model,
validator,
)
from pydantic.main import ModelMetaclass
try:
from pydantic.v1 import (
BaseModel,
ConstrainedStr,
Field,
StrictBool,
StrictFloat,
StrictInt,
StrictStr,
ValidationError,
create_model,
validator,
)
from pydantic.v1.main import ModelMetaclass
except ImportError:
from pydantic import ( # type: ignore
BaseModel,
ConstrainedStr,
Field,
StrictBool,
StrictFloat,
StrictInt,
StrictStr,
ValidationError,
create_model,
validator,
)
from pydantic.main import ModelMetaclass # type: ignore
from thinc.api import ConfigValidationError, Model, Optimizer
from thinc.config import Promise
@ -397,6 +412,7 @@ class ConfigSchemaNlp(BaseModel):
after_creation: Optional[Callable[["Language"], "Language"]] = Field(..., title="Optional callback to modify nlp object after creation and before the pipeline is constructed")
after_pipeline_creation: Optional[Callable[["Language"], "Language"]] = Field(..., title="Optional callback to modify nlp object after the pipeline is constructed")
batch_size: Optional[int] = Field(..., title="Default batch size")
vectors: Callable = Field(..., title="Vectors implementation")
# fmt: on
class Config:
@ -488,66 +504,6 @@ CONFIG_SCHEMAS = {
"distillation": ConfigSchemaDistill,
}
# Project config Schema
class ProjectConfigAssetGitItem(BaseModel):
# fmt: off
repo: StrictStr = Field(..., title="URL of Git repo to download from")
path: StrictStr = Field(..., title="File path or sub-directory to download (used for sparse checkout)")
branch: StrictStr = Field("master", title="Branch to clone from")
# fmt: on
class ProjectConfigAssetURL(BaseModel):
# fmt: off
dest: StrictStr = Field(..., title="Destination of downloaded asset")
url: Optional[StrictStr] = Field(None, title="URL of asset")
checksum: Optional[str] = Field(None, title="MD5 hash of file", regex=r"([a-fA-F\d]{32})")
description: StrictStr = Field("", title="Description of asset")
# fmt: on
class ProjectConfigAssetGit(BaseModel):
# fmt: off
git: ProjectConfigAssetGitItem = Field(..., title="Git repo information")
checksum: Optional[str] = Field(None, title="MD5 hash of file", regex=r"([a-fA-F\d]{32})")
description: Optional[StrictStr] = Field(None, title="Description of asset")
# fmt: on
class ProjectConfigCommand(BaseModel):
# fmt: off
name: StrictStr = Field(..., title="Name of command")
help: Optional[StrictStr] = Field(None, title="Command description")
script: List[StrictStr] = Field([], title="List of CLI commands to run, in order")
deps: List[StrictStr] = Field([], title="File dependencies required by this command")
outputs: List[StrictStr] = Field([], title="Outputs produced by this command")
outputs_no_cache: List[StrictStr] = Field([], title="Outputs not tracked by DVC (DVC only)")
no_skip: bool = Field(False, title="Never skip this command, even if nothing changed")
# fmt: on
class Config:
title = "A single named command specified in a project config"
extra = "forbid"
class ProjectConfigSchema(BaseModel):
# fmt: off
vars: Dict[StrictStr, Any] = Field({}, title="Optional variables to substitute in commands")
env: Dict[StrictStr, Any] = Field({}, title="Optional variable names to substitute in commands, mapped to environment variable names")
assets: List[Union[ProjectConfigAssetURL, ProjectConfigAssetGit]] = Field([], title="Data assets")
workflows: Dict[StrictStr, List[StrictStr]] = Field({}, title="Named workflows, mapped to list of project commands to run in order")
commands: List[ProjectConfigCommand] = Field([], title="Project command shortucts")
title: Optional[str] = Field(None, title="Project title")
spacy_version: Optional[StrictStr] = Field(None, title="spaCy version range that the project is compatible with")
# fmt: on
class Config:
title = "Schema for project configuration file"
# Recommendations for init config workflows

138
spacy/scorer.py
View File

@ -802,6 +802,140 @@ def get_ner_prf(examples: Iterable[Example], **kwargs) -> Dict[str, Any]:
}
# The following implementation of trapezoid() is adapted from SciPy,
# which is distributed under the New BSD License.
# Copyright (c) 2001-2002 Enthought, Inc. 2003-2023, SciPy Developers.
# See licenses/3rd_party_licenses.txt
def trapezoid(y, x=None, dx=1.0, axis=-1):
r"""
Integrate along the given axis using the composite trapezoidal rule.
If `x` is provided, the integration happens in sequence along its
elements - they are not sorted.
Integrate `y` (`x`) along each 1d slice on the given axis, compute
:math:`\int y(x) dx`.
When `x` is specified, this integrates along the parametric curve,
computing :math:`\int_t y(t) dt =
\int_t y(t) \left.\frac{dx}{dt}\right|_{x=x(t)} dt`.
Parameters
----------
y : array_like
Input array to integrate.
x : array_like, optional
The sample points corresponding to the `y` values. If `x` is None,
the sample points are assumed to be evenly spaced `dx` apart. The
default is None.
dx : scalar, optional
The spacing between sample points when `x` is None. The default is 1.
axis : int, optional
The axis along which to integrate.
Returns
-------
trapezoid : float or ndarray
Definite integral of `y` = n-dimensional array as approximated along
a single axis by the trapezoidal rule. If `y` is a 1-dimensional array,
then the result is a float. If `n` is greater than 1, then the result
is an `n`-1 dimensional array.
See Also
--------
cumulative_trapezoid, simpson, romb
Notes
-----
Image [2]_ illustrates trapezoidal rule -- y-axis locations of points
will be taken from `y` array, by default x-axis distances between
points will be 1.0, alternatively they can be provided with `x` array
or with `dx` scalar. Return value will be equal to combined area under
the red lines.
References
----------
.. [1] Wikipedia page: https://en.wikipedia.org/wiki/Trapezoidal_rule
.. [2] Illustration image:
https://en.wikipedia.org/wiki/File:Composite_trapezoidal_rule_illustration.png
Examples
--------
Use the trapezoidal rule on evenly spaced points:
>>> import numpy as np
>>> from scipy import integrate
>>> integrate.trapezoid([1, 2, 3])
4.0
The spacing between sample points can be selected by either the
``x`` or ``dx`` arguments:
>>> integrate.trapezoid([1, 2, 3], x=[4, 6, 8])
8.0
>>> integrate.trapezoid([1, 2, 3], dx=2)
8.0
Using a decreasing ``x`` corresponds to integrating in reverse:
>>> integrate.trapezoid([1, 2, 3], x=[8, 6, 4])
-8.0
More generally ``x`` is used to integrate along a parametric curve. We can
estimate the integral :math:`\int_0^1 x^2 = 1/3` using:
>>> x = np.linspace(0, 1, num=50)
>>> y = x**2
>>> integrate.trapezoid(y, x)
0.33340274885464394
Or estimate the area of a circle, noting we repeat the sample which closes
the curve:
>>> theta = np.linspace(0, 2 * np.pi, num=1000, endpoint=True)
>>> integrate.trapezoid(np.cos(theta), x=np.sin(theta))
3.141571941375841
``trapezoid`` can be applied along a specified axis to do multiple
computations in one call:
>>> a = np.arange(6).reshape(2, 3)
>>> a
array([[0, 1, 2],
[3, 4, 5]])
>>> integrate.trapezoid(a, axis=0)
array([1.5, 2.5, 3.5])
>>> integrate.trapezoid(a, axis=1)
array([2., 8.])
"""
y = np.asanyarray(y)
if x is None:
d = dx
else:
x = np.asanyarray(x)
if x.ndim == 1:
d = np.diff(x)
# reshape to correct shape
shape = [1] * y.ndim
shape[axis] = d.shape[0]
d = d.reshape(shape)
else:
d = np.diff(x, axis=axis)
nd = y.ndim
slice1 = [slice(None)] * nd
slice2 = [slice(None)] * nd
slice1[axis] = slice(1, None)
slice2[axis] = slice(None, -1)
try:
ret = (d * (y[tuple(slice1)] + y[tuple(slice2)]) / 2.0).sum(axis)
except ValueError:
# Operations didn't work, cast to ndarray
d = np.asarray(d)
y = np.asarray(y)
ret = np.add.reduce(d * (y[tuple(slice1)] + y[tuple(slice2)]) / 2.0, axis)
return ret
# The following implementation of roc_auc_score() is adapted from
# scikit-learn, which is distributed under the New BSD License.
# Copyright (c) 2007–2019 The scikit-learn developers.
@ -1024,9 +1158,9 @@ def _auc(x, y):
else:
raise ValueError(Errors.E164.format(x=x))
area = direction * np.trapz(y, x)
area = direction * trapezoid(y, x)
if isinstance(area, np.memmap):
# Reductions such as .sum used internally in np.trapz do not return a
# Reductions such as .sum used internally in trapezoid do not return a
# scalar by default for numpy.memmap instances contrary to
# regular numpy.ndarray instances.
area = area.dtype.type(area)

1
spacy/strings.pyx
View File

@ -1,4 +1,5 @@
# cython: infer_types=True
# cython: profile=False
from typing import Iterable, Iterator, List, Optional, Tuple, Union
from libc.stdint cimport uint32_t

1
spacy/symbols.pyx
View File

@ -1,4 +1,5 @@
# cython: optimize.unpack_method_calls=False
# cython: profile=False
IDS = {
"": NIL,
"IS_ALPHA": IS_ALPHA,

10
spacy/tests/conftest.py
View File

@ -194,6 +194,11 @@ def fi_tokenizer():
return get_lang_class("fi")().tokenizer
@pytest.fixture(scope="session")
def fo_tokenizer():
return get_lang_class("fo")().tokenizer
@pytest.fixture(scope="session")
def fr_tokenizer():
return get_lang_class("fr")().tokenizer
@ -363,6 +368,11 @@ def nl_tokenizer():
return get_lang_class("nl")().tokenizer
@pytest.fixture(scope="session")
def nn_tokenizer():
return get_lang_class("nn")().tokenizer
@pytest.fixture(scope="session")
def pl_tokenizer():
return get_lang_class("pl")().tokenizer

9
spacy/tests/doc/test_span.py
View File

@ -783,3 +783,12 @@ def test_for_no_ent_sents():
sents = list(doc.ents[0].sents)
assert len(sents) == 1
assert str(sents[0]) == str(doc.ents[0].sent) == "ENTITY"
def test_span_api_richcmp_other(en_tokenizer):
doc1 = en_tokenizer("a b")
doc2 = en_tokenizer("b c")
assert not doc1[1:2] == doc1[1]
assert not doc1[1:2] == doc2[0]
assert not doc1[1:2] == doc2[0:1]
assert not doc1[0:1] == doc2

9
spacy/tests/doc/test_token_api.py
View File

@ -294,3 +294,12 @@ def test_missing_head_dep(en_vocab):
assert aligned_heads[0] == ref_heads[0]
assert aligned_deps[5] == ref_deps[5]
assert aligned_heads[5] == ref_heads[5]
def test_token_api_richcmp_other(en_tokenizer):
doc1 = en_tokenizer("a b")
doc2 = en_tokenizer("b c")
assert not doc1[1] == doc1[0:1]
assert not doc1[1] == doc2[1:2]
assert not doc1[1] == doc2[0]
assert not doc1[0] == doc2

0
spacy/tests/lang/fo/__init__.py Normal file
View File

26
spacy/tests/lang/fo/test_tokenizer.py Normal file
View File

@ -0,0 +1,26 @@
import pytest
# examples taken from Basic LAnguage Resource Kit 1.0 for Faroese (https://maltokni.fo/en/resources) licensed with CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
# fmt: off
FO_TOKEN_EXCEPTION_TESTS = [
(
"Eftir løgtingslóg um samsýning og eftirløn landsstýrismanna v.m., skulu løgmaður og landsstýrismenn vanliga siga frá sær størv í almennari tænastu ella privatum virkjum, samtøkum ella stovnum. ",
[
"Eftir", "løgtingslóg", "um", "samsýning", "og", "eftirløn", "landsstýrismanna", "v.m.", ",", "skulu", "løgmaður", "og", "landsstýrismenn", "vanliga", "siga", "frá", "sær", "størv", "í", "almennari", "tænastu", "ella", "privatum", "virkjum", ",", "samtøkum", "ella", "stovnum", ".",
],
),
(
"Sambandsflokkurin gongur aftur við 2,7 prosentum í mun til valið í 1994, tá flokkurin fekk undirtøku frá 23,4 prosent av veljarunum.",
[
"Sambandsflokkurin", "gongur", "aftur", "við", "2,7", "prosentum", "í", "mun", "til", "valið", "í", "1994", ",", "tá", "flokkurin", "fekk", "undirtøku", "frá", "23,4", "prosent", "av", "veljarunum", ".",
],
),
]
# fmt: on
@pytest.mark.parametrize("text,expected_tokens", FO_TOKEN_EXCEPTION_TESTS)
def test_fo_tokenizer_handles_exception_cases(fo_tokenizer, text, expected_tokens):
tokens = fo_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list

0
spacy/tests/lang/nn/__init__.py Normal file
View File

38
spacy/tests/lang/nn/test_tokenizer.py Normal file
View File

@ -0,0 +1,38 @@
import pytest
# examples taken from Omsetjingsminne frå Nynorsk pressekontor 2022 (https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-80/)
# fmt: off
NN_TOKEN_EXCEPTION_TESTS = [
(
"Målet til direktoratet er at alle skal bli tilbydd jobb i politiet så raskt som mogleg i 2014.",
[
"Målet", "til", "direktoratet", "er", "at", "alle", "skal", "bli", "tilbydd", "jobb", "i", "politiet", "så", "raskt", "som", "mogleg", "i", "2014", ".",
],
),
(
"Han ønskjer ikkje at staten skal vere med på å finansiere slik undervisning, men dette er rektor på skulen ueinig i.",
[
"Han", "ønskjer", "ikkje", "at", "staten", "skal", "vere", "med", "på", "å", "finansiere", "slik", "undervisning", ",", "men", "dette", "er", "rektor", "på", "skulen", "ueinig", "i", ".",
],
),
(
"Ifølgje China Daily vart det 8.848 meter høge fjellet flytta 3 centimeter sørvestover under jordskjelvet, som vart målt til 7,8.",
[
"Ifølgje", "China", "Daily", "vart", "det", "8.848", "meter", "høge", "fjellet", "flytta", "3", "centimeter", "sørvestover", "under", "jordskjelvet", ",", "som", "vart", "målt", "til", "7,8", ".",
],
),
(
"Brukssesongen er frå nov. til mai, med ein topp i mars.",
[
"Brukssesongen", "er", "frå", "nov.", "til", "mai", ",", "med", "ein", "topp", "i", "mars", ".",
],
),
]
# fmt: on
@pytest.mark.parametrize("text,expected_tokens", NN_TOKEN_EXCEPTION_TESTS)
def test_nn_tokenizer_handles_exception_cases(nn_tokenizer, text, expected_tokens):
tokens = nn_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list

5
spacy/tests/matcher/test_dependency_matcher.py
View File

@ -216,6 +216,11 @@ def test_dependency_matcher_pattern_validation(en_vocab):
pattern2 = copy.deepcopy(pattern)
pattern2[1]["RIGHT_ID"] = "fox"
matcher.add("FOUNDED", [pattern2])
# invalid key
with pytest.warns(UserWarning):
pattern2 = copy.deepcopy(pattern)
pattern2[1]["FOO"] = "BAR"
matcher.add("FOUNDED", [pattern2])
def test_dependency_matcher_callback(en_vocab, doc):

2
spacy/tests/package/test_requirements.py
View File

@ -5,6 +5,7 @@ from pathlib import Path
def test_build_dependencies():
# Check that library requirements are pinned exactly the same across different setup files.
libs_ignore_requirements = [
"numpy",
"pytest",
"pytest-timeout",
"mock",
@ -22,6 +23,7 @@ def test_build_dependencies():
]
# ignore language-specific packages that shouldn't be installed by all
libs_ignore_setup = [
"numpy",
"fugashi",
"mecab-ko",
"pythainlp",

7
spacy/tests/pipeline/test_initialize.py
View File

@ -1,5 +1,10 @@
import pytest
from pydantic import StrictBool
try:
from pydantic.v1 import StrictBool
except ImportError:
from pydantic import StrictBool # type: ignore
from thinc.api import ConfigValidationError
from spacy.lang.en import English

9
spacy/tests/pipeline/test_pipe_factories.py
View File

@ -1,5 +1,10 @@
import pytest
from pydantic import StrictInt, StrictStr
try:
from pydantic.v1 import StrictInt, StrictStr
except ImportError:
from pydantic import StrictInt, StrictStr # type: ignore
from thinc.api import ConfigValidationError, Linear, Model
import spacy
@ -198,7 +203,7 @@ def test_pipe_class_component_model():
"@architectures": "spacy.TextCatEnsemble.v2",
"tok2vec": DEFAULT_TOK2VEC_MODEL,
"linear_model": {
"@architectures": "spacy.TextCatBOW.v2",
"@architectures": "spacy.TextCatBOW.v3",
"exclusive_classes": False,
"ngram_size": 1,
"no_output_layer": False,

Some files were not shown because too many files have changed in this diff Show More