Merge pull request #11270 from adrianeboyd/chore/update-develop-v3.5

Prepare develop for v3.5

.github/azure-steps.yml

@@ -27,7 +27,6 @@ steps:
 
   - script: python -m mypy spacy
     displayName: 'Run mypy'
-    condition: ne(variables['python_version'], '3.10')
 
   - task: DeleteFiles@1
     inputs:
@@ -41,7 +40,7 @@ steps:
 
   - bash: |
       ${{ parameters.prefix }} SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
-      ${{ parameters.prefix }} python -m pip install dist/$SDIST
+      ${{ parameters.prefix }} SPACY_NUM_BUILD_JOBS=2 python -m pip install dist/$SDIST
     displayName: "Install from sdist"
 
   - script: |
@@ -111,7 +110,7 @@ steps:
     condition: eq(variables['python_version'], '3.8')
 
   - script: |
-      ${{ parameters.prefix }} python -m pip install thinc-apple-ops
+      ${{ parameters.prefix }} python -m pip install --pre thinc-apple-ops
       ${{ parameters.prefix }} python -m pytest --pyargs spacy
     displayName: "Run CPU tests with thinc-apple-ops"
-    condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.9'))
+    condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.10'))

.github/contributors/Lucaterre.md

@@ -0,0 +1,106 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI GmbH](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+    * you hereby assign to us joint ownership, and to the extent that such
+    assignment is or becomes invalid, ineffective or unenforceable, you hereby
+    grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+    royalty-free, unrestricted license to exercise all rights under those
+    copyrights. This includes, at our option, the right to sublicense these same
+    rights to third parties through multiple levels of sublicensees or other
+    licensing arrangements;
+
+    * you agree that each of us can do all things in relation to your
+    contribution as if each of us were the sole owners, and if one of us makes
+    a derivative work of your contribution, the one who makes the derivative
+    work (or has it made will be the sole owner of that derivative work;
+
+    * you agree that you will not assert any moral rights in your contribution
+    against us, our licensees or transferees;
+
+    * you agree that we may register a copyright in your contribution and
+    exercise all ownership rights associated with it; and
+
+    * you agree that neither of us has any duty to consult with, obtain the
+    consent of, pay or render an accounting to the other for any use or
+    distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+    * make, have made, use, sell, offer to sell, import, and otherwise transfer
+    your contribution in whole or in part, alone or in combination with or
+    included in any product, work or materials arising out of the project to
+    which your contribution was submitted, and
+
+    * at our option, to sublicense these same rights to third parties through
+    multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+    * Each contribution that you submit is and shall be an original work of
+    authorship and you can legally grant the rights set out in this SCA;
+
+    * to the best of your knowledge, each contribution will not violate any
+    third party's copyrights, trademarks, patents, or other intellectual
+    property rights; and
+
+    * each contribution shall be in compliance with U.S. export control laws and
+    other applicable export and import laws. You agree to notify us if you
+    become aware of any circumstance which would make any of the foregoing
+    representations inaccurate in any respect. We may publicly disclose your
+    participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+    * [x] I am signing on behalf of myself as an individual and no other person
+    or entity, including my employer, has or will have rights with respect to my
+    contributions.
+
+    * [ ] I am signing on behalf of my employer or a legal entity and I have the
+    actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field                          | Entry         |
+|------------------------------- |---------------|
+| Name                           | Lucas Terriel |
+| Company name (if applicable)   |               |
+| Title or role (if applicable)  |               |
+| Date                           | 2022-06-20    |
+| GitHub username                | Lucaterre     |
+| Website (optional)             |               |

.github/spacy_universe_alert.py

@@ -0,0 +1,67 @@
+import os
+import sys
+import json
+from datetime import datetime
+
+from slack_sdk.web.client import WebClient
+
+CHANNEL = "#alerts-universe"
+SLACK_TOKEN = os.environ.get("SLACK_BOT_TOKEN", "ENV VAR not available!")
+DATETIME_FORMAT = "%Y-%m-%dT%H:%M:%SZ"
+
+client = WebClient(SLACK_TOKEN)
+github_context = json.loads(sys.argv[1])
+
+event = github_context['event']
+pr_title = event['pull_request']["title"]
+pr_link = event['pull_request']["patch_url"].replace(".patch", "")
+pr_author_url = event['sender']["html_url"]
+pr_author_name = pr_author_url.rsplit('/')[-1]
+pr_created_at_dt = datetime.strptime(
+    event['pull_request']["created_at"],
+    DATETIME_FORMAT
+)
+pr_created_at = pr_created_at_dt.strftime("%c")
+pr_updated_at_dt = datetime.strptime(
+    event['pull_request']["updated_at"],
+    DATETIME_FORMAT
+)
+pr_updated_at = pr_updated_at_dt.strftime("%c")
+
+blocks = [
+    {
+      "type": "section",
+      "text": {
+        "type": "mrkdwn",
+        "text": "📣 New spaCy Universe Project Alert ✨"
+      }
+    },
+    {
+      "type": "section",
+      "fields": [
+        {
+          "type": "mrkdwn",
+          "text": f"*Pull Request:*\n<{pr_link}|{pr_title}>"
+        },
+        {
+          "type": "mrkdwn",
+          "text": f"*Author:*\n<{pr_author_url}|{pr_author_name}>"
+        },
+        {
+          "type": "mrkdwn",
+          "text": f"*Created at:*\n {pr_created_at}"
+        },
+        {
+          "type": "mrkdwn",
+          "text": f"*Last Updated:*\n {pr_updated_at}"
+        }
+      ]
+    }
+  ]
+
+
+client.chat_postMessage(
+    channel=CHANNEL,
+    text="spaCy universe project PR alert",
+    blocks=blocks
+)

.github/workflows/explosionbot.yml

@@ -23,5 +23,5 @@ jobs:
         env:
           INPUT_TOKEN: ${{ secrets.EXPLOSIONBOT_TOKEN }}
           INPUT_BK_TOKEN: ${{ secrets.BUILDKITE_SECRET }}
-          ENABLED_COMMANDS: "test_gpu,test_slow"
+          ENABLED_COMMANDS: "test_gpu,test_slow,test_slow_gpu"
           ALLOWED_TEAMS: "spaCy"

.github/workflows/gputests.yml

@@ -10,6 +10,7 @@ jobs:
       fail-fast: false
       matrix:
         branch: [master, v4]
+    if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
     steps:
       - name: Trigger buildkite build

.github/workflows/slowtests.yml

@@ -10,6 +10,7 @@ jobs:
       fail-fast: false
       matrix:
         branch: [master, v4]
+    if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
     steps:
       - name: Checkout

.github/workflows/spacy_universe_alert.yml

@@ -0,0 +1,30 @@
+name: spaCy universe project alert
+
+on:
+  pull_request_target:
+    paths:
+      - "website/meta/universe.json"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Dump GitHub context
+        env:
+          GITHUB_CONTEXT: ${{ toJson(github) }}
+          PR_NUMBER: ${{github.event.number}}
+        run: |
+          echo "$GITHUB_CONTEXT"
+
+      - uses: actions/checkout@v1
+      - uses: actions/setup-python@v1
+      - name: Install Bernadette app dependency and send an alert
+        env:
+          SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+          GITHUB_CONTEXT: ${{ toJson(github) }}
+          CHANNEL: "#alerts-universe"
+        run: |
+          pip install slack-sdk==3.17.2 aiohttp==3.8.1
+          echo "$CHANNEL"
+          python .github/spacy_universe_alert.py "$GITHUB_CONTEXT"

CONTRIBUTING.md

@@ -271,7 +271,8 @@ except:  # noqa: E722
 
 ### Python conventions
 
-All Python code must be written **compatible with Python 3.6+**.
+All Python code must be written **compatible with Python 3.6+**. More detailed
+code conventions can be found in the [developer docs](https://github.com/explosion/spaCy/blob/master/extra/DEVELOPER_DOCS/Code%20Conventions.md).
 
 #### I/O and handling paths
 

MANIFEST.in

@@ -1,4 +1,4 @@
-recursive-include spacy *.pyi *.pyx *.pxd *.txt *.cfg *.jinja *.toml
+recursive-include spacy *.pyi *.pyx *.pxd *.txt *.cfg *.jinja *.toml *.hh
 include LICENSE
 include README.md
 include pyproject.toml

README.md

@@ -16,7 +16,7 @@ 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.
 
-💫 **Version 3.2 out now!**
+💫 **Version 3.4.0 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)

build-constraints.txt

@@ -1,6 +1,8 @@
 # build version constraints for use with wheelwright + multibuild
-numpy==1.15.0; python_version<='3.7'
+numpy==1.15.0; python_version<='3.7' and platform_machine!='aarch64'
-numpy==1.17.3; python_version=='3.8'
+numpy==1.19.2; python_version<='3.7' and platform_machine=='aarch64'
+numpy==1.17.3; python_version=='3.8' and platform_machine!='aarch64'
+numpy==1.19.2; python_version=='3.8' and platform_machine=='aarch64'
 numpy==1.19.3; python_version=='3.9'
 numpy==1.21.3; python_version=='3.10'
 numpy; python_version>='3.11'

extra/DEVELOPER_DOCS/Code Conventions.md

@@ -455,6 +455,10 @@ Regression tests are tests that refer to bugs reported in specific issues. They
 
 The test suite also provides [fixtures](https://github.com/explosion/spaCy/blob/master/spacy/tests/conftest.py) for different language tokenizers that can be used as function arguments of the same name and will be passed in automatically. Those should only be used for tests related to those specific languages. We also have [test utility functions](https://github.com/explosion/spaCy/blob/master/spacy/tests/util.py) for common operations, like creating a temporary file.
 
+### Testing Cython Code
+
+If you're developing Cython code (`.pyx` files), those extensions will need to be built before the test runner can test that code - otherwise it's going to run the tests with stale code from the last time the extension was built. You can build the extensions locally with `python setup.py build_ext -i`.
+
 ### Constructing objects and state
 
 Test functions usually follow the same simple structure: they set up some state, perform the operation you want to test and `assert` conditions that you expect to be true, usually before and after the operation.

extra/DEVELOPER_DOCS/ExplosionBot.md

@@ -16,17 +16,37 @@ To summon the robot, write a github comment on the issue/PR you wish to test. Th
 
 Some things to note:
 
-* The `@explosion-bot please` must be the beginning of the command - you cannot add anything in front of this or else the robot won't know how to parse it. Adding anything at the end aside from the test name will also confuse the robot, so keep it simple!
+- The `@explosion-bot please` must be the beginning of the command - you cannot add anything in front of this or else the robot won't know how to parse it. Adding anything at the end aside from the test name will also confuse the robot, so keep it simple!
-* The command name (such as `test_gpu`) must be one of the tests that the bot knows how to run. The available commands are documented in the bot's [workflow config](https://github.com/explosion/spaCy/blob/master/.github/workflows/explosionbot.yml#L26) and must match exactly one of the commands listed there.
+- The command name (such as `test_gpu`) must be one of the tests that the bot knows how to run. The available commands are documented in the bot's [workflow config](https://github.com/explosion/spaCy/blob/master/.github/workflows/explosionbot.yml#L26) and must match exactly one of the commands listed there.
-* The robot can't do multiple things at once, so if you want it to run multiple tests, you'll have to summon it with one comment per test.
+- The robot can't do multiple things at once, so if you want it to run multiple tests, you'll have to summon it with one comment per test.
-* For the `test_gpu` command, you can specify an optional thinc branch (from the spaCy repo) or a spaCy branch (from the thinc repo) with either the `--thinc-branch` or `--spacy-branch` flags. By default, the bot will pull in the PR branch from the repo where the command was issued, and the main branch of the other repository. However, if you need to run against another branch, you can say (for example):
+
+### Examples
+
+- Execute spaCy slow GPU tests with a custom thinc branch from a spaCy PR:
 
   ```
-@explosion-bot please test_gpu --thinc-branch develop
+  @explosion-bot please test_slow_gpu --thinc-branch <branch_name>
   ```
-You can also specify a branch from an unmerged PR:
+
+  `branch_name` can either be a named branch, e.g: `develop`, or an unmerged PR, e.g: `refs/pull/<pr_number>/head`.
+
+- Execute spaCy Transformers GPU tests from a spaCy PR:
+
   ```
-@explosion-bot please test_gpu --thinc-branch refs/pull/633/head
+  @explosion-bot please test_gpu --run-on spacy-transformers --run-on-branch master --spacy-branch current_pr
+  ```
+
+  This will launch the GPU pipeline for the `spacy-transformers` repo on its `master` branch, using the current spaCy PR's branch to build spaCy. The name of the repository passed to `--run-on` is case-sensitive, e.g: use `spaCy` instead of `spacy`.
+
+- General info about supported commands.
+
+  ```
+  @explosion-bot please info
+  ```
+
+- Help text for a specific command
+  ```
+  @explosion-bot please <command> --help
   ```
 
 ## Troubleshooting

pyproject.toml

@@ -5,8 +5,7 @@ requires = [
     "cymem>=2.0.2,<2.1.0",
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
-    "thinc>=8.0.14,<8.1.0",
+    "thinc>=8.1.0,<8.2.0",
-    "blis>=0.4.0,<0.8.0",
     "pathy",
     "numpy>=1.15.0",
 ]

requirements.txt

@@ -3,8 +3,7 @@ spacy-legacy>=3.0.9,<3.1.0
 spacy-loggers>=1.0.0,<2.0.0
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
-thinc>=8.0.14,<8.1.0
+thinc>=8.1.0,<8.2.0
-blis>=0.4.0,<0.8.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.1.0
@@ -16,13 +15,13 @@ pathy>=0.3.5
 numpy>=1.15.0
 requests>=2.13.0,<3.0.0
 tqdm>=4.38.0,<5.0.0
-pydantic>=1.7.4,!=1.8,!=1.8.1,<1.9.0
+pydantic>=1.7.4,!=1.8,!=1.8.1,<1.10.0
 jinja2
 langcodes>=3.2.0,<4.0.0
 # Official Python utilities
 setuptools
 packaging>=20.0
-typing_extensions>=3.7.4.1,<4.0.0.0; python_version < "3.8"
+typing_extensions>=3.7.4.1,<4.2.0; python_version < "3.8"
 # Development dependencies
 pre-commit>=2.13.0
 cython>=0.25,<3.0
@@ -31,7 +30,7 @@ pytest-timeout>=1.3.0,<2.0.0
 mock>=2.0.0,<3.0.0
 flake8>=3.8.0,<3.10.0
 hypothesis>=3.27.0,<7.0.0
-mypy==0.910
+mypy>=0.910,<0.970; platform_machine!='aarch64'
 types-dataclasses>=0.1.3; python_version < "3.7"
 types-mock>=0.1.1
 types-requests

setup.cfg

@@ -38,7 +38,7 @@ setup_requires =
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
     murmurhash>=0.28.0,<1.1.0
-    thinc>=8.0.14,<8.1.0
+    thinc>=8.1.0,<8.2.0
 install_requires =
     # Our libraries
     spacy-legacy>=3.0.9,<3.1.0
@@ -46,8 +46,7 @@ install_requires =
     murmurhash>=0.28.0,<1.1.0
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
-    thinc>=8.0.14,<8.1.0
+    thinc>=8.1.0,<8.2.0
-    blis>=0.4.0,<0.8.0
     wasabi>=0.9.1,<1.1.0
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
@@ -57,12 +56,12 @@ install_requires =
     tqdm>=4.38.0,<5.0.0
     numpy>=1.15.0
     requests>=2.13.0,<3.0.0
-    pydantic>=1.7.4,!=1.8,!=1.8.1,<1.9.0
+    pydantic>=1.7.4,!=1.8,!=1.8.1,<1.10.0
     jinja2
     # Official Python utilities
     setuptools
     packaging>=20.0
-    typing_extensions>=3.7.4,<4.0.0.0; python_version < "3.8"
+    typing_extensions>=3.7.4,<4.2.0; python_version < "3.8"
     langcodes>=3.2.0,<4.0.0
 
 [options.entry_points]
@@ -104,14 +103,18 @@ cuda114 =
     cupy-cuda114>=5.0.0b4,<11.0.0
 cuda115 =
     cupy-cuda115>=5.0.0b4,<11.0.0
+cuda116 =
+    cupy-cuda116>=5.0.0b4,<11.0.0
+cuda117 =
+    cupy-cuda117>=5.0.0b4,<11.0.0
 apple =
-    thinc-apple-ops>=0.0.4,<1.0.0
+    thinc-apple-ops>=0.1.0.dev0,<1.0.0
 # Language tokenizers with external dependencies
 ja =
     sudachipy>=0.5.2,!=0.6.1
     sudachidict_core>=20211220
 ko =
-    natto-py==0.9.0
+    natto-py>=0.9.0
 th =
     pythainlp>=2.0
 

setup.py

@@ -126,6 +126,8 @@ class build_ext_options:
 
 class build_ext_subclass(build_ext, build_ext_options):
     def build_extensions(self):
+        if self.parallel is None and os.environ.get("SPACY_NUM_BUILD_JOBS") is not None:
+            self.parallel = int(os.environ.get("SPACY_NUM_BUILD_JOBS"))
         build_ext_options.build_options(self)
         build_ext.build_extensions(self)
 
@@ -206,7 +208,11 @@ def setup_package():
     for name in MOD_NAMES:
         mod_path = name.replace(".", "/") + ".pyx"
         ext = Extension(
-            name, [mod_path], language="c++", include_dirs=include_dirs, extra_compile_args=["-std=c++11"]
+            name,
+            [mod_path],
+            language="c++",
+            include_dirs=include_dirs,
+            extra_compile_args=["-std=c++11"],
         )
         ext_modules.append(ext)
     print("Cythonizing sources")

spacy/__init__.py

@@ -32,6 +32,7 @@ def load(
     *,
     vocab: Union[Vocab, bool] = True,
     disable: Iterable[str] = util.SimpleFrozenList(),
+    enable: Iterable[str] = util.SimpleFrozenList(),
     exclude: Iterable[str] = util.SimpleFrozenList(),
     config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(),
 ) -> Language:
@@ -42,6 +43,8 @@ def load(
     disable (Iterable[str]): Names of pipeline components to disable. Disabled
         pipes will be loaded but they won't be run unless you explicitly
         enable them by calling nlp.enable_pipe.
+    enable (Iterable[str]): Names of pipeline components to enable. All other
+        pipes will be disabled (but can be enabled later using nlp.enable_pipe).
     exclude (Iterable[str]): Names of pipeline components to exclude. Excluded
         components won't be loaded.
     config (Dict[str, Any] / Config): Config overrides as nested dict or dict
@@ -49,7 +52,12 @@ def load(
     RETURNS (Language): The loaded nlp object.
     """
     return util.load_model(
-        name, vocab=vocab, disable=disable, exclude=exclude, config=config
+        name,
+        vocab=vocab,
+        disable=disable,
+        enable=enable,
+        exclude=exclude,
+        config=config,
     )
 
 

spacy/about.py

@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.3.0"
+__version__ = "3.4.1"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
 __projects__ = "https://github.com/explosion/projects"

spacy/cli/_util.py

@@ -12,7 +12,7 @@ from click.parser import split_arg_string
 from typer.main import get_command
 from contextlib import contextmanager
 from thinc.api import Config, ConfigValidationError, require_gpu
-from thinc.util import has_cupy, gpu_is_available
+from thinc.util import gpu_is_available
 from configparser import InterpolationError
 import os
 
@@ -462,6 +462,23 @@ def git_sparse_checkout(repo, subpath, dest, branch):
         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]:
@@ -554,5 +571,5 @@ def setup_gpu(use_gpu: int, silent=None) -> None:
         require_gpu(use_gpu)
     else:
         local_msg.info("Using CPU")
-        if has_cupy and gpu_is_available():
+        if gpu_is_available():
             local_msg.info("To switch to GPU 0, use the option: --gpu-id 0")

spacy/cli/debug_data.py

@@ -6,10 +6,11 @@ import sys
 import srsly
 from wasabi import Printer, MESSAGES, msg
 import typer
+import math
 
 from ._util import app, Arg, Opt, show_validation_error, parse_config_overrides
 from ._util import import_code, debug_cli
-from ..training import Example
+from ..training import Example, remove_bilu_prefix
 from ..training.initialize import get_sourced_components
 from ..schemas import ConfigSchemaTraining
 from ..pipeline._parser_internals import nonproj
@@ -30,6 +31,12 @@ DEP_LABEL_THRESHOLD = 20
 # Minimum number of expected examples to train a new pipeline
 BLANK_MODEL_MIN_THRESHOLD = 100
 BLANK_MODEL_THRESHOLD = 2000
+# Arbitrary threshold where SpanCat performs well
+SPAN_DISTINCT_THRESHOLD = 1
+# Arbitrary threshold where SpanCat performs well
+BOUNDARY_DISTINCT_THRESHOLD = 1
+# Arbitrary threshold for filtering span lengths during reporting (percentage)
+SPAN_LENGTH_THRESHOLD_PERCENTAGE = 90
 
 
 @debug_cli.command(
@@ -247,6 +254,69 @@ def debug_data(
                     msg.warn(f"No examples for texts WITHOUT new label '{label}'")
                     has_no_neg_warning = True
 
+            with msg.loading("Obtaining span characteristics..."):
+                span_characteristics = _get_span_characteristics(
+                    train_dataset, gold_train_data, spans_key
+                )
+
+            msg.info(f"Span characteristics for spans_key '{spans_key}'")
+            msg.info("SD = Span Distinctiveness, BD = Boundary Distinctiveness")
+            _print_span_characteristics(span_characteristics)
+
+            _span_freqs = _get_spans_length_freq_dist(
+                gold_train_data["spans_length"][spans_key]
+            )
+            _filtered_span_freqs = _filter_spans_length_freq_dist(
+                _span_freqs, threshold=SPAN_LENGTH_THRESHOLD_PERCENTAGE
+            )
+
+            msg.info(
+                f"Over {SPAN_LENGTH_THRESHOLD_PERCENTAGE}% of spans have lengths of 1 -- "
+                f"{max(_filtered_span_freqs.keys())} "
+                f"(min={span_characteristics['min_length']}, max={span_characteristics['max_length']}). "
+                f"The most common span lengths are: {_format_freqs(_filtered_span_freqs)}. "
+                "If you are using the n-gram suggester, note that omitting "
+                "infrequent n-gram lengths can greatly improve speed and "
+                "memory usage."
+            )
+
+            msg.text(
+                f"Full distribution of span lengths: {_format_freqs(_span_freqs)}",
+                show=verbose,
+            )
+
+            # Add report regarding span characteristics
+            if span_characteristics["avg_sd"] < SPAN_DISTINCT_THRESHOLD:
+                msg.warn("Spans may not be distinct from the rest of the corpus")
+            else:
+                msg.good("Spans are distinct from the rest of the corpus")
+
+            p_spans = span_characteristics["p_spans"].values()
+            all_span_tokens: Counter = sum(p_spans, Counter())
+            most_common_spans = [w for w, _ in all_span_tokens.most_common(10)]
+            msg.text(
+                "10 most common span tokens: {}".format(
+                    _format_labels(most_common_spans)
+                ),
+                show=verbose,
+            )
+
+            # Add report regarding span boundary characteristics
+            if span_characteristics["avg_bd"] < BOUNDARY_DISTINCT_THRESHOLD:
+                msg.warn("Boundary tokens are not distinct from the rest of the corpus")
+            else:
+                msg.good("Boundary tokens are distinct from the rest of the corpus")
+
+            p_bounds = span_characteristics["p_bounds"].values()
+            all_span_bound_tokens: Counter = sum(p_bounds, Counter())
+            most_common_bounds = [w for w, _ in all_span_bound_tokens.most_common(10)]
+            msg.text(
+                "10 most common span boundary tokens: {}".format(
+                    _format_labels(most_common_bounds)
+                ),
+                show=verbose,
+            )
+
         if has_low_data_warning:
             msg.text(
                 f"To train a new span type, your data should include at "
@@ -291,7 +361,7 @@ def debug_data(
             if label != "-"
         ]
         labels_with_counts = _format_labels(labels_with_counts, counts=True)
-        msg.text(f"Labels in train data: {_format_labels(labels)}", show=verbose)
+        msg.text(f"Labels in train data: {labels_with_counts}", show=verbose)
         missing_labels = model_labels - labels
         if missing_labels:
             msg.warn(
@@ -647,6 +717,9 @@ def _compile_gold(
         "words": Counter(),
         "roots": Counter(),
         "spancat": dict(),
+        "spans_length": dict(),
+        "spans_per_type": dict(),
+        "sb_per_type": dict(),
         "ws_ents": 0,
         "boundary_cross_ents": 0,
         "n_words": 0,
@@ -685,21 +758,66 @@ def _compile_gold(
                     # "Illegal" whitespace entity
                     data["ws_ents"] += 1
                 if label.startswith(("B-", "U-")):
-                    combined_label = label.split("-")[1]
+                    combined_label = remove_bilu_prefix(label)
                     data["ner"][combined_label] += 1
-                if sent_starts[i] == True and label.startswith(("I-", "L-")):
+                if sent_starts[i] and label.startswith(("I-", "L-")):
                     data["boundary_cross_ents"] += 1
                 elif label == "-":
                     data["ner"]["-"] += 1
         if "spancat" in factory_names:
-            for span_key in list(eg.reference.spans.keys()):
+            for spans_key in list(eg.reference.spans.keys()):
-                if span_key not in data["spancat"]:
+                # Obtain the span frequency
-                    data["spancat"][span_key] = Counter()
+                if spans_key not in data["spancat"]:
-                for i, span in enumerate(eg.reference.spans[span_key]):
+                    data["spancat"][spans_key] = Counter()
+                for i, span in enumerate(eg.reference.spans[spans_key]):
                     if span.label_ is None:
                         continue
                     else:
-                        data["spancat"][span_key][span.label_] += 1
+                        data["spancat"][spans_key][span.label_] += 1
+
+                # Obtain the span length
+                if spans_key not in data["spans_length"]:
+                    data["spans_length"][spans_key] = dict()
+                for span in gold.spans[spans_key]:
+                    if span.label_ is None:
+                        continue
+                    if span.label_ not in data["spans_length"][spans_key]:
+                        data["spans_length"][spans_key][span.label_] = []
+                    data["spans_length"][spans_key][span.label_].append(len(span))
+
+                # Obtain spans per span type
+                if spans_key not in data["spans_per_type"]:
+                    data["spans_per_type"][spans_key] = dict()
+                for span in gold.spans[spans_key]:
+                    if span.label_ not in data["spans_per_type"][spans_key]:
+                        data["spans_per_type"][spans_key][span.label_] = []
+                    data["spans_per_type"][spans_key][span.label_].append(span)
+
+                # Obtain boundary tokens per span type
+                window_size = 1
+                if spans_key not in data["sb_per_type"]:
+                    data["sb_per_type"][spans_key] = dict()
+                for span in gold.spans[spans_key]:
+                    if span.label_ not in data["sb_per_type"][spans_key]:
+                        # Creating a data structure that holds the start and
+                        # end tokens for each span type
+                        data["sb_per_type"][spans_key][span.label_] = {
+                            "start": [],
+                            "end": [],
+                        }
+                    for offset in range(window_size):
+                        sb_start_idx = span.start - (offset + 1)
+                        if sb_start_idx >= 0:
+                            data["sb_per_type"][spans_key][span.label_]["start"].append(
+                                gold[sb_start_idx : sb_start_idx + 1]
+                            )
+
+                        sb_end_idx = span.end + (offset + 1)
+                        if sb_end_idx <= len(gold):
+                            data["sb_per_type"][spans_key][span.label_]["end"].append(
+                                gold[sb_end_idx - 1 : sb_end_idx]
+                            )
+
         if "textcat" in factory_names or "textcat_multilabel" in factory_names:
             data["cats"].update(gold.cats)
             if any(val not in (0, 1) for val in gold.cats.values()):
@@ -770,6 +888,16 @@ def _format_labels(
     return ", ".join([f"'{l}'" for l in cast(Iterable[str], labels)])
 
 
+def _format_freqs(freqs: Dict[int, float], sort: bool = True) -> str:
+    if sort:
+        freqs = dict(sorted(freqs.items()))
+
+    _freqs = [(str(k), v) for k, v in freqs.items()]
+    return ", ".join(
+        [f"{l} ({c}%)" for l, c in cast(Iterable[Tuple[str, float]], _freqs)]
+    )
+
+
 def _get_examples_without_label(
     data: Sequence[Example],
     label: str,
@@ -780,7 +908,7 @@ def _get_examples_without_label(
     for eg in data:
         if component == "ner":
             labels = [
-                label.split("-")[1]
+                remove_bilu_prefix(label)
                 for label in eg.get_aligned_ner()
                 if label not in ("O", "-", None)
             ]
@@ -824,3 +952,158 @@ def _get_labels_from_spancat(nlp: Language) -> Dict[str, Set[str]]:
             labels[pipe.key] = set()
         labels[pipe.key].update(pipe.labels)
     return labels
+
+
+def _gmean(l: List) -> float:
+    """Compute geometric mean of a list"""
+    return math.exp(math.fsum(math.log(i) for i in l) / len(l))
+
+
+def _wgt_average(metric: Dict[str, float], frequencies: Counter) -> float:
+    total = sum(value * frequencies[span_type] for span_type, value in metric.items())
+    return total / sum(frequencies.values())
+
+
+def _get_distribution(docs, normalize: bool = True) -> Counter:
+    """Get the frequency distribution given a set of Docs"""
+    word_counts: Counter = Counter()
+    for doc in docs:
+        for token in doc:
+            # Normalize the text
+            t = token.text.lower().replace("``", '"').replace("''", '"')
+            word_counts[t] += 1
+    if normalize:
+        total = sum(word_counts.values(), 0.0)
+        word_counts = Counter({k: v / total for k, v in word_counts.items()})
+    return word_counts
+
+
+def _get_kl_divergence(p: Counter, q: Counter) -> float:
+    """Compute the Kullback-Leibler divergence from two frequency distributions"""
+    total = 0.0
+    for word, p_word in p.items():
+        total += p_word * math.log(p_word / q[word])
+    return total
+
+
+def _format_span_row(span_data: List[Dict], labels: List[str]) -> List[Any]:
+    """Compile into one list for easier reporting"""
+    d = {
+        label: [label] + list(round(d[label], 2) for d in span_data) for label in labels
+    }
+    return list(d.values())
+
+
+def _get_span_characteristics(
+    examples: List[Example], compiled_gold: Dict[str, Any], spans_key: str
+) -> Dict[str, Any]:
+    """Obtain all span characteristics"""
+    data_labels = compiled_gold["spancat"][spans_key]
+    # Get lengths
+    span_length = {
+        label: _gmean(l)
+        for label, l in compiled_gold["spans_length"][spans_key].items()
+    }
+    min_lengths = [min(l) for l in compiled_gold["spans_length"][spans_key].values()]
+    max_lengths = [max(l) for l in compiled_gold["spans_length"][spans_key].values()]
+
+    # Get relevant distributions: corpus, spans, span boundaries
+    p_corpus = _get_distribution([eg.reference for eg in examples], normalize=True)
+    p_spans = {
+        label: _get_distribution(spans, normalize=True)
+        for label, spans in compiled_gold["spans_per_type"][spans_key].items()
+    }
+    p_bounds = {
+        label: _get_distribution(sb["start"] + sb["end"], normalize=True)
+        for label, sb in compiled_gold["sb_per_type"][spans_key].items()
+    }
+
+    # Compute for actual span characteristics
+    span_distinctiveness = {
+        label: _get_kl_divergence(freq_dist, p_corpus)
+        for label, freq_dist in p_spans.items()
+    }
+    sb_distinctiveness = {
+        label: _get_kl_divergence(freq_dist, p_corpus)
+        for label, freq_dist in p_bounds.items()
+    }
+
+    return {
+        "sd": span_distinctiveness,
+        "bd": sb_distinctiveness,
+        "lengths": span_length,
+        "min_length": min(min_lengths),
+        "max_length": max(max_lengths),
+        "avg_sd": _wgt_average(span_distinctiveness, data_labels),
+        "avg_bd": _wgt_average(sb_distinctiveness, data_labels),
+        "avg_length": _wgt_average(span_length, data_labels),
+        "labels": list(data_labels.keys()),
+        "p_spans": p_spans,
+        "p_bounds": p_bounds,
+    }
+
+
+def _print_span_characteristics(span_characteristics: Dict[str, Any]):
+    """Print all span characteristics into a table"""
+    headers = ("Span Type", "Length", "SD", "BD")
+    # Prepare table data with all span characteristics
+    table_data = [
+        span_characteristics["lengths"],
+        span_characteristics["sd"],
+        span_characteristics["bd"],
+    ]
+    table = _format_span_row(
+        span_data=table_data, labels=span_characteristics["labels"]
+    )
+    # Prepare table footer with weighted averages
+    footer_data = [
+        span_characteristics["avg_length"],
+        span_characteristics["avg_sd"],
+        span_characteristics["avg_bd"],
+    ]
+    footer = ["Wgt. Average"] + [str(round(f, 2)) for f in footer_data]
+    msg.table(table, footer=footer, header=headers, divider=True)
+
+
+def _get_spans_length_freq_dist(
+    length_dict: Dict, threshold=SPAN_LENGTH_THRESHOLD_PERCENTAGE
+) -> Dict[int, float]:
+    """Get frequency distribution of spans length under a certain threshold"""
+    all_span_lengths = []
+    for _, lengths in length_dict.items():
+        all_span_lengths.extend(lengths)
+
+    freq_dist: Counter = Counter()
+    for i in all_span_lengths:
+        if freq_dist.get(i):
+            freq_dist[i] += 1
+        else:
+            freq_dist[i] = 1
+
+    # We will be working with percentages instead of raw counts
+    freq_dist_percentage = {}
+    for span_length, count in freq_dist.most_common():
+        percentage = (count / len(all_span_lengths)) * 100.0
+        percentage = round(percentage, 2)
+        freq_dist_percentage[span_length] = percentage
+
+    return freq_dist_percentage
+
+
+def _filter_spans_length_freq_dist(
+    freq_dist: Dict[int, float], threshold: int
+) -> Dict[int, float]:
+    """Filter frequency distribution with respect to a threshold
+
+    We're going to filter all the span lengths that fall
+    around a percentage threshold when summed.
+    """
+    total = 0.0
+    filtered_freq_dist = {}
+    for span_length, dist in freq_dist.items():
+        if total >= threshold:
+            break
+        else:
+            filtered_freq_dist[span_length] = dist
+        total += dist
+    return filtered_freq_dist

spacy/cli/download.py

@@ -7,6 +7,7 @@ import typer
 from ._util import app, Arg, Opt, WHEEL_SUFFIX, SDIST_SUFFIX
 from .. import about
 from ..util import is_package, get_minor_version, run_command
+from ..util import is_prerelease_version
 from ..errors import OLD_MODEL_SHORTCUTS
 
 
@@ -74,6 +75,9 @@ def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -
 
 
 def get_compatibility() -> dict:
+    if is_prerelease_version(about.__version__):
+        version: Optional[str] = about.__version__
+    else:
         version = get_minor_version(about.__version__)
     r = requests.get(about.__compatibility__)
     if r.status_code != 200:

spacy/cli/init_config.py

@@ -10,6 +10,7 @@ from jinja2 import Template
 from .. import util
 from ..language import DEFAULT_CONFIG_PRETRAIN_PATH
 from ..schemas import RecommendationSchema
+from ..util import SimpleFrozenList
 from ._util import init_cli, Arg, Opt, show_validation_error, COMMAND
 from ._util import string_to_list, import_code
 
@@ -24,16 +25,30 @@ class Optimizations(str, Enum):
     accuracy = "accuracy"
 
 
+class InitValues:
+    """
+    Default values for initialization. Dedicated class to allow synchronized default values for init_config_cli() and
+    init_config(), i.e. initialization calls via CLI respectively Python.
+    """
+
+    lang = "en"
+    pipeline = SimpleFrozenList(["tagger", "parser", "ner"])
+    optimize = Optimizations.efficiency
+    gpu = False
+    pretraining = False
+    force_overwrite = False
+
+
 @init_cli.command("config")
 def init_config_cli(
     # fmt: off
     output_file: Path = Arg(..., help="File to save the config to or - for stdout (will only output config and no additional logging info)", allow_dash=True),
-    lang: str = Opt("en", "--lang", "-l", help="Two-letter code of the language to use"),
+    lang: str = Opt(InitValues.lang, "--lang", "-l", help="Two-letter code of the language to use"),
-    pipeline: str = Opt("tagger,parser,ner", "--pipeline", "-p", help="Comma-separated names of trainable pipeline components to include (without 'tok2vec' or 'transformer')"),
+    pipeline: str = Opt(",".join(InitValues.pipeline), "--pipeline", "-p", help="Comma-separated names of trainable pipeline components to include (without 'tok2vec' or 'transformer')"),
-    optimize: Optimizations = Opt(Optimizations.efficiency.value, "--optimize", "-o", help="Whether to optimize for efficiency (faster inference, smaller model, lower memory consumption) or higher accuracy (potentially larger and slower model). This will impact the choice of architecture, pretrained weights and related hyperparameters."),
+    optimize: Optimizations = Opt(InitValues.optimize, "--optimize", "-o", help="Whether to optimize for efficiency (faster inference, smaller model, lower memory consumption) or higher accuracy (potentially larger and slower model). This will impact the choice of architecture, pretrained weights and related hyperparameters."),
-    gpu: bool = Opt(False, "--gpu", "-G", help="Whether the model can run on GPU. This will impact the choice of architecture, pretrained weights and related hyperparameters."),
+    gpu: bool = Opt(InitValues.gpu, "--gpu", "-G", help="Whether the model can run on GPU. This will impact the choice of architecture, pretrained weights and related hyperparameters."),
-    pretraining: bool = Opt(False, "--pretraining", "-pt", help="Include config for pretraining (with 'spacy pretrain')"),
+    pretraining: bool = Opt(InitValues.pretraining, "--pretraining", "-pt", help="Include config for pretraining (with 'spacy pretrain')"),
-    force_overwrite: bool = Opt(False, "--force", "-F", help="Force overwriting the output file"),
+    force_overwrite: bool = Opt(InitValues.force_overwrite, "--force", "-F", help="Force overwriting the output file"),
     # fmt: on
 ):
     """
@@ -133,11 +148,11 @@ def fill_config(
 
 def init_config(
     *,
-    lang: str,
+    lang: str = InitValues.lang,
-    pipeline: List[str],
+    pipeline: List[str] = InitValues.pipeline,
-    optimize: str,
+    optimize: str = InitValues.optimize,
-    gpu: bool,
+    gpu: bool = InitValues.gpu,
-    pretraining: bool = False,
+    pretraining: bool = InitValues.pretraining,
     silent: bool = True,
 ) -> Config:
     msg = Printer(no_print=silent)

spacy/cli/pretrain.py

@@ -61,7 +61,7 @@ def pretrain_cli(
         # TODO: What's the solution here? How do we handle optional blocks?
         msg.fail("The [pretraining] block in your config is empty", exits=1)
     if not output_dir.exists():
-        output_dir.mkdir()
+        output_dir.mkdir(parents=True)
         msg.good(f"Created output directory: {output_dir}")
     # Save non-interpolated config
     raw_config.to_disk(output_dir / "config.cfg")

spacy/cli/project/assets.py

@@ -12,6 +12,9 @@ from .._util import project_cli, Arg, Opt, PROJECT_FILE, load_project_config
 from .._util import get_checksum, download_file, git_checkout, get_git_version
 from .._util import SimpleFrozenDict, parse_config_overrides
 
+# Whether assets are extra if `extra` is not set.
+EXTRA_DEFAULT = False
+
 
 @project_cli.command(
     "assets",
@@ -21,7 +24,8 @@ 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+.")
+    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
@@ -32,7 +36,12 @@ def project_assets_cli(
     DOCS: https://spacy.io/api/cli#project-assets
     """
     overrides = parse_config_overrides(ctx.args)
-    project_assets(project_dir, overrides=overrides, sparse_checkout=sparse_checkout)
+    project_assets(
+        project_dir,
+        overrides=overrides,
+        sparse_checkout=sparse_checkout,
+        extra=extra,
+    )
 
 
 def project_assets(
@@ -40,17 +49,29 @@ def project_assets(
     *,
     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 = config.get("assets", {})
+    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}", exits=0)
+        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")

spacy/cli/project/clone.py

@@ -7,11 +7,11 @@ import re
 from ... import about
 from ...util import ensure_path
 from .._util import project_cli, Arg, Opt, COMMAND, PROJECT_FILE
-from .._util import git_checkout, get_git_version
+from .._util import git_checkout, get_git_version, git_repo_branch_exists
 
 DEFAULT_REPO = about.__projects__
 DEFAULT_PROJECTS_BRANCH = about.__projects_branch__
-DEFAULT_BRANCH = "master"
+DEFAULT_BRANCHES = ["main", "master"]
 
 
 @project_cli.command("clone")
@@ -20,7 +20,7 @@ def project_clone_cli(
     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="The branch 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
 ):
@@ -33,9 +33,25 @@ def project_clone_cli(
     """
     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:
-        # If it's a user repo, we want to default to other branch
+        for default_branch in DEFAULT_BRANCHES:
-        branch = DEFAULT_PROJECTS_BRANCH if repo == DEFAULT_REPO else DEFAULT_BRANCH
+            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)
 
 
@@ -61,9 +77,9 @@ def project_clone(
     try:
         git_checkout(repo, name, dest, branch=branch, sparse=sparse_checkout)
     except subprocess.CalledProcessError:
-        err = f"Could not clone '{name}' from repo '{repo_name}'"
+        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}", project_dir)
+    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:

spacy/displacy/render.py

@@ -64,8 +64,11 @@ class SpanRenderer:
         # Set up how the text and labels will be rendered
         self.direction = DEFAULT_DIR
         self.lang = DEFAULT_LANG
+        # These values are in px
         self.top_offset = options.get("top_offset", 40)
-        self.top_offset_step = options.get("top_offset_step", 17)
+        # This is how far under the top offset the span labels appear
+        self.span_label_offset = options.get("span_label_offset", 20)
+        self.offset_step = options.get("top_offset_step", 17)
 
         # Set up which templates will be used
         template = options.get("template")
@@ -127,26 +130,56 @@ class SpanRenderer:
         title (str / None): Document title set in Doc.user_data['title'].
         """
         per_token_info = []
+        # 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
+        spans = sorted(
+            spans,
+            key=lambda s: (
+                s["start_token"],
+                -(s["end_token"] - s["start_token"]),
+                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
             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"] = True if idx == span["start_token"] else False
+                    ent["is_start"] = span_start
+                    if span_start:
+                        # 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
+                    ent["render_slot"] = span["render_slot"]
                     kb_id = span.get("kb_id", "")
                     kb_url = span.get("kb_url", "#")
                     ent["kb_link"] = (
                         TPL_KB_LINK.format(kb_id=kb_id, kb_url=kb_url) if kb_id else ""
                     )
                     entities.append(ent)
+                else:
+                    # We don't specifically need to do this since we loop
+                    # over tokens and spans sorted by their start_token,
+                    # so we'll never use a span again after the last token it appears in,
+                    # but if we were to use these spans again we'd want to make sure
+                    # this value was reset correctly.
+                    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:
@@ -157,12 +190,24 @@ class SpanRenderer:
         """Render the markup from per-token information"""
         markup = ""
         for token in per_token_info:
-            entities = sorted(token["entities"], key=lambda d: d["label"])
+            entities = sorted(token["entities"], key=lambda d: d["render_slot"])
-            if entities:
+            # Whitespace tokens disrupt the vertical space (no line height) so that the
+            # span indicators get misaligned. We don't render them as individual
+            # tokens anyway, so we'll just not display a span indicator either.
+            is_whitespace = token["text"].strip() == ""
+            if entities and not is_whitespace:
                 slices = self._get_span_slices(token["entities"])
                 starts = self._get_span_starts(token["entities"])
+                total_height = (
+                    self.top_offset
+                    + self.span_label_offset
+                    + (self.offset_step * (len(entities) - 1))
+                )
                 markup += self.span_template.format(
-                    text=token["text"], span_slices=slices, span_starts=starts
+                    text=token["text"],
+                    span_slices=slices,
+                    span_starts=starts,
+                    total_height=total_height,
                 )
             else:
                 markup += escape_html(token["text"] + " ")
@@ -171,10 +216,18 @@ class SpanRenderer:
     def _get_span_slices(self, entities: List[Dict]) -> str:
         """Get the rendered markup of all Span slices"""
         span_slices = []
-        for entity, step in zip(entities, itertools.count(step=self.top_offset_step)):
+        for entity in entities:
+            # rather than iterate over multiples of offset_step, we use entity['render_slot']
+            # to determine the vertical position, since that tells where
+            # the span starts vertically so we can extend it horizontally,
+            # past other spans that might have already ended
             color = self.colors.get(entity["label"].upper(), self.default_color)
+            top_offset = self.top_offset + (
+                self.offset_step * (entity["render_slot"] - 1)
+            )
             span_slice = self.span_slice_template.format(
-                bg=color, top_offset=self.top_offset + step
+                bg=color,
+                top_offset=top_offset,
             )
             span_slices.append(span_slice)
         return "".join(span_slices)
@@ -182,12 +235,15 @@ class SpanRenderer:
     def _get_span_starts(self, entities: List[Dict]) -> str:
         """Get the rendered markup of all Span start tokens"""
         span_starts = []
-        for entity, step in zip(entities, itertools.count(step=self.top_offset_step)):
+        for entity in entities:
             color = self.colors.get(entity["label"].upper(), self.default_color)
+            top_offset = self.top_offset + (
+                self.offset_step * (entity["render_slot"] - 1)
+            )
             span_start = (
                 self.span_start_template.format(
                     bg=color,
-                    top_offset=self.top_offset + step,
+                    top_offset=top_offset,
                     label=entity["label"],
                     kb_link=entity["kb_link"],
                 )

spacy/displacy/templates.py

@@ -67,7 +67,7 @@ TPL_SPANS = """
 """
 
 TPL_SPAN = """
-<span style="font-weight: bold; display: inline-block; position: relative;">
+<span style="font-weight: bold; display: inline-block; position: relative; height: {total_height}px;">
     {text}
     {span_slices}
     {span_starts}

spacy/errors.py

@@ -1,4 +1,5 @@
 import warnings
+from .compat import Literal
 
 
 class ErrorsWithCodes(type):
@@ -26,7 +27,10 @@ def setup_default_warnings():
     filter_warning("once", error_msg="[W114]")
 
 
-def filter_warning(action: str, error_msg: str):
+def filter_warning(
+    action: Literal["default", "error", "ignore", "always", "module", "once"],
+    error_msg: str,
+):
     """Customize how spaCy should handle a certain warning.
 
     error_msg (str): e.g. "W006", or a full error message
@@ -199,6 +203,15 @@ class Warnings(metaclass=ErrorsWithCodes):
     W118 = ("Term '{term}' not found in glossary. It may however be explained in documentation "
             "for the corpora used to train the language. Please check "
             "`nlp.meta[\"sources\"]` for any relevant links.")
+    W119 = ("Overriding pipe name in `config` is not supported. Ignoring override '{name_in_config}'.")
+    W120 = ("Unable to load all spans in Doc.spans: more than one span group "
+            "with the name '{group_name}' was found in the saved spans data. "
+            "Only the last span group will be loaded under "
+            "Doc.spans['{group_name}']. Skipping span group with values: "
+            "{group_values}")
+    W121 = ("Attempting to trace non-existent method '{method}' in pipe '{pipe}'")
+    W122 = ("Couldn't trace method '{method}' in pipe '{pipe}'. This can happen if the pipe class "
+            "is a Cython extension type.")
 
 
 class Errors(metaclass=ErrorsWithCodes):
@@ -444,10 +457,10 @@ class Errors(metaclass=ErrorsWithCodes):
             "same, but found '{nlp}' and '{vocab}' respectively.")
     E152 = ("The attribute {attr} is not supported for token patterns. "
             "Please use the option `validate=True` with the Matcher, PhraseMatcher, "
-            "or EntityRuler for more details.")
+            "EntityRuler or AttributeRuler for more details.")
     E153 = ("The value type {vtype} is not supported for token patterns. "
             "Please use the option validate=True with Matcher, PhraseMatcher, "
-            "or EntityRuler for more details.")
+            "EntityRuler or AttributeRuler for more details.")
     E154 = ("One of the attributes or values is not supported for token "
             "patterns. Please use the option `validate=True` with the Matcher, "
             "PhraseMatcher, or EntityRuler for more details.")
@@ -527,6 +540,8 @@ class Errors(metaclass=ErrorsWithCodes):
     E202 = ("Unsupported {name} mode '{mode}'. Supported modes: {modes}.")
 
     # New errors added in v3.x
+    E854 = ("Unable to set doc.ents. Check that the 'ents_filter' does not "
+            "permit overlapping spans.")
     E855 = ("Invalid {obj}: {obj} is not from the same doc.")
     E856 = ("Error accessing span at position {i}: out of bounds in span group "
             "of length {length}.")
@@ -898,8 +913,8 @@ class Errors(metaclass=ErrorsWithCodes):
     E1022 = ("Words must be of type str or int, but input is of type '{wtype}'")
     E1023 = ("Couldn't read EntityRuler from the {path}. This file doesn't "
              "exist.")
-    E1024 = ("A pattern with ID \"{ent_id}\" is not present in EntityRuler "
+    E1024 = ("A pattern with {attr_type} '{label}' is not present in "
-             "patterns.")
+             "'{component}' patterns.")
     E1025 = ("Cannot intify the value '{value}' as an IOB string. The only "
              "supported values are: 'I', 'O', 'B' and ''")
     E1026 = ("Edit tree has an invalid format:\n{errors}")
@@ -913,6 +928,17 @@ class Errors(metaclass=ErrorsWithCodes):
     E1034 = ("Node index {i} out of bounds ({length})")
     E1035 = ("Token index {i} out of bounds ({length})")
     E1036 = ("Cannot index into NoneNode")
+    E1037 = ("Invalid attribute value '{attr}'.")
+    E1038 = ("Invalid JSON input: {message}")
+    E1039 = ("The {obj} start or end annotations (start: {start}, end: {end}) "
+             "could not be aligned to token boundaries.")
+    E1040 = ("Doc.from_json requires all tokens to have the same attributes. "
+             "Some tokens do not contain annotation for: {partial_attrs}")
+    E1041 = ("Expected a string, Doc, or bytes as input, but got: {type}")
+    E1042 = ("Function was called with `{arg1}`={arg1_values} and "
+             "`{arg2}`={arg2_values} but these arguments are conflicting.")
+    E1043 = ("Expected None or a value in range [{range_start}, {range_end}] for entity linker threshold, but got "
+             "{value}.")
 
 
 # Deprecated model shortcuts, only used in errors and warnings

spacy/glossary.py

@@ -273,6 +273,7 @@ GLOSSARY = {
     "relcl": "relative clause modifier",
     "reparandum": "overridden disfluency",
     "root": "root",
+    "ROOT": "root",
     "vocative": "vocative",
     "xcomp": "open clausal complement",
     # Dependency labels (German)

spacy/kb.pyx

@@ -93,14 +93,14 @@ cdef class KnowledgeBase:
         self.vocab = vocab
         self._create_empty_vectors(dummy_hash=self.vocab.strings[""])
 
-    def initialize_entities(self, int64_t nr_entities):
+    def _initialize_entities(self, int64_t nr_entities):
         self._entry_index = PreshMap(nr_entities + 1)
         self._entries = entry_vec(nr_entities + 1)
 
-    def initialize_vectors(self, int64_t nr_entities):
+    def _initialize_vectors(self, int64_t nr_entities):
         self._vectors_table = float_matrix(nr_entities + 1)
 
-    def initialize_aliases(self, int64_t nr_aliases):
+    def _initialize_aliases(self, int64_t nr_aliases):
         self._alias_index = PreshMap(nr_aliases + 1)
         self._aliases_table = alias_vec(nr_aliases + 1)
 
@@ -155,8 +155,8 @@ cdef class KnowledgeBase:
             raise ValueError(Errors.E140)
 
         nr_entities = len(set(entity_list))
-        self.initialize_entities(nr_entities)
+        self._initialize_entities(nr_entities)
-        self.initialize_vectors(nr_entities)
+        self._initialize_vectors(nr_entities)
 
         i = 0
         cdef KBEntryC entry
@@ -388,9 +388,9 @@ cdef class KnowledgeBase:
             nr_entities = header[0]
             nr_aliases = header[1]
             entity_vector_length = header[2]
-            self.initialize_entities(nr_entities)
+            self._initialize_entities(nr_entities)
-            self.initialize_vectors(nr_entities)
+            self._initialize_vectors(nr_entities)
-            self.initialize_aliases(nr_aliases)
+            self._initialize_aliases(nr_aliases)
             self.entity_vector_length = entity_vector_length
 
         def deserialize_vectors(b):
@@ -512,8 +512,8 @@ cdef class KnowledgeBase:
         cdef int64_t entity_vector_length
         reader.read_header(&nr_entities, &entity_vector_length)
 
-        self.initialize_entities(nr_entities)
+        self._initialize_entities(nr_entities)
-        self.initialize_vectors(nr_entities)
+        self._initialize_vectors(nr_entities)
         self.entity_vector_length = entity_vector_length
 
         # STEP 1: load entity vectors
@@ -552,7 +552,7 @@ cdef class KnowledgeBase:
         # STEP 3: load aliases
         cdef int64_t nr_aliases
         reader.read_alias_length(&nr_aliases)
-        self.initialize_aliases(nr_aliases)
+        self._initialize_aliases(nr_aliases)
 
         cdef int64_t nr_candidates
         cdef vector[int64_t] entry_indices

spacy/lang/bg/__init__.py

@@ -2,7 +2,8 @@ from .stop_words import STOP_WORDS
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 from .lex_attrs import LEX_ATTRS
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-
+from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_INFIXES
+from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
 from ...language import Language, BaseDefaults
 from ...attrs import LANG
 from ...util import update_exc
@@ -16,6 +17,8 @@ class BulgarianDefaults(BaseDefaults):
 
     stop_words = STOP_WORDS
     tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
+    suffixes = COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
+    infixes = COMBINING_DIACRITICS_TOKENIZER_INFIXES
 
 
 class Bulgarian(Language):

spacy/lang/char_classes.py

@@ -258,6 +258,10 @@ ALPHA = group_chars(
 ALPHA_LOWER = group_chars(_lower + _uncased)
 ALPHA_UPPER = group_chars(_upper + _uncased)
 
+_combining_diacritics = r"\u0300-\u036f"
+
+COMBINING_DIACRITICS = _combining_diacritics
+
 _units = (
     "km km² km³ m m² m³ dm dm² dm³ cm cm² cm³ mm mm² mm³ ha µm nm yd in ft "
     "kg g mg µg t lb oz m/s km/h kmh mph hPa Pa mbar mb MB kb KB gb GB tb "

spacy/lang/en/tokenizer_exceptions.py

@@ -35,7 +35,7 @@ for pron in ["i"]:
 
         _exc[orth + "m"] = [
             {ORTH: orth, NORM: pron},
-            {ORTH: "m", "tenspect": 1, "number": 1},
+            {ORTH: "m"},
         ]
 
         _exc[orth + "'ma"] = [
@@ -139,20 +139,21 @@ for pron in ["he", "she", "it"]:
 
 # W-words, relative pronouns, prepositions etc.
 
-for word in [
+for word, morph in [
-    "who",
+    ("who", None),
-    "what",
+    ("what", None),
-    "when",
+    ("when", None),
-    "where",
+    ("where", None),
-    "why",
+    ("why", None),
-    "how",
+    ("how", None),
-    "there",
+    ("there", None),
-    "that",
+    ("that", "Number=Sing|Person=3"),
-    "this",
+    ("this", "Number=Sing|Person=3"),
-    "these",
+    ("these", "Number=Plur|Person=3"),
-    "those",
+    ("those", "Number=Plur|Person=3"),
 ]:
     for orth in [word, word.title()]:
+        if morph != "Number=Plur|Person=3":
             _exc[orth + "'s"] = [
                 {ORTH: orth, NORM: word},
                 {ORTH: "'s", NORM: "'s"},
@@ -182,6 +183,7 @@ for word in [
             {ORTH: "ve", NORM: "have"},
         ]
 
+        if morph != "Number=Sing|Person=3":
             _exc[orth + "'re"] = [
                 {ORTH: orth, NORM: word},
                 {ORTH: "'re", NORM: "are"},

spacy/lang/punctuation.py

@@ -1,5 +1,5 @@
 from .char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY
-from .char_classes import LIST_ICONS, HYPHENS, CURRENCY, UNITS
+from .char_classes import LIST_ICONS, HYPHENS, CURRENCY, UNITS, COMBINING_DIACRITICS
 from .char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA, PUNCT
 
 
@@ -44,3 +44,23 @@ TOKENIZER_INFIXES = (
         r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
     ]
 )
+
+
+# Some languages e.g. written with the Cyrillic alphabet permit the use of diacritics
+# to mark stressed syllables in words where stress is distinctive. Such languages
+# should use the COMBINING_DIACRITICS... suffix and infix regex lists in
+# place of the standard ones.
+COMBINING_DIACRITICS_TOKENIZER_SUFFIXES = list(TOKENIZER_SUFFIXES) + [
+    r"(?<=[{a}][{d}])\.".format(a=ALPHA, d=COMBINING_DIACRITICS),
+]
+
+COMBINING_DIACRITICS_TOKENIZER_INFIXES = list(TOKENIZER_INFIXES) + [
+    r"(?<=[{al}][{d}])\.(?=[{au}{q}])".format(
+        al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES, d=COMBINING_DIACRITICS
+    ),
+    r"(?<=[{a}][{d}]),(?=[{a}])".format(a=ALPHA, d=COMBINING_DIACRITICS),
+    r"(?<=[{a}][{d}])(?:{h})(?=[{a}])".format(
+        a=ALPHA, d=COMBINING_DIACRITICS, h=HYPHENS
+    ),
+    r"(?<=[{a}][{d}])[:<>=/](?=[{a}])".format(a=ALPHA, d=COMBINING_DIACRITICS),
+]

spacy/lang/ru/__init__.py

@@ -5,6 +5,8 @@ from .stop_words import STOP_WORDS
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 from .lex_attrs import LEX_ATTRS
 from .lemmatizer import RussianLemmatizer
+from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_INFIXES
+from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
 from ...language import Language, BaseDefaults
 
 
@@ -12,6 +14,8 @@ class RussianDefaults(BaseDefaults):
     tokenizer_exceptions = TOKENIZER_EXCEPTIONS
     lex_attr_getters = LEX_ATTRS
     stop_words = STOP_WORDS
+    suffixes = COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
+    infixes = COMBINING_DIACRITICS_TOKENIZER_INFIXES
 
 
 class Russian(Language):

spacy/lang/uk/__init__.py

@@ -6,6 +6,8 @@ from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 from .stop_words import STOP_WORDS
 from .lex_attrs import LEX_ATTRS
 from .lemmatizer import UkrainianLemmatizer
+from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_INFIXES
+from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
 from ...language import Language, BaseDefaults
 
 
@@ -13,6 +15,8 @@ class UkrainianDefaults(BaseDefaults):
     tokenizer_exceptions = TOKENIZER_EXCEPTIONS
     lex_attr_getters = LEX_ATTRS
     stop_words = STOP_WORDS
+    suffixes = COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
+    infixes = COMBINING_DIACRITICS_TOKENIZER_INFIXES
 
 
 class Ukrainian(Language):

spacy/language.py

@@ -1,4 +1,4 @@
-from typing import Iterator, Optional, Any, Dict, Callable, Iterable
+from typing import Iterator, Optional, Any, Dict, Callable, Iterable, Collection
 from typing import Union, Tuple, List, Set, Pattern, Sequence
 from typing import NoReturn, TYPE_CHECKING, TypeVar, cast, overload
 
@@ -774,6 +774,9 @@ class Language:
         name = name if name is not None else factory_name
         if name in self.component_names:
             raise ValueError(Errors.E007.format(name=name, opts=self.component_names))
+        # Overriding pipe name in the config is not supported and will be ignored.
+        if "name" in config:
+            warnings.warn(Warnings.W119.format(name_in_config=config.pop("name")))
         if source is not None:
             # We're loading the component from a model. After loading the
             # component, we know its real factory name
@@ -1087,16 +1090,21 @@ class Language:
             )
         return self.tokenizer(text)
 
-    def _ensure_doc(self, doc_like: Union[str, Doc]) -> Doc:
+    def _ensure_doc(self, doc_like: Union[str, Doc, bytes]) -> Doc:
-        """Create a Doc if need be, or raise an error if the input is not a Doc or a string."""
+        """Create a Doc if need be, or raise an error if the input is not
+        a Doc, string, or a byte array (generated by Doc.to_bytes())."""
         if isinstance(doc_like, Doc):
             return doc_like
         if isinstance(doc_like, str):
             return self.make_doc(doc_like)
-        raise ValueError(Errors.E866.format(type=type(doc_like)))
+        if isinstance(doc_like, bytes):
+            return Doc(self.vocab).from_bytes(doc_like)
+        raise ValueError(Errors.E1041.format(type=type(doc_like)))
 
-    def _ensure_doc_with_context(self, doc_like: Union[str, Doc], context: Any) -> Doc:
+    def _ensure_doc_with_context(
-        """Create a Doc if need be and add as_tuples context, or raise an error if the input is not a Doc or a string."""
+        self, doc_like: Union[str, Doc, bytes], context: _AnyContext
+    ) -> Doc:
+        """Call _ensure_doc to generate a Doc and set its context object."""
         doc = self._ensure_doc(doc_like)
         doc._context = context
         return doc
@@ -1516,7 +1524,6 @@ class Language:
 
         DOCS: https://spacy.io/api/language#pipe
         """
-        # Handle texts with context as tuples
         if as_tuples:
             texts = cast(Iterable[Tuple[Union[str, Doc], _AnyContext]], texts)
             docs_with_contexts = (
@@ -1594,8 +1601,21 @@ class Language:
         n_process: int,
         batch_size: int,
     ) -> Iterator[Doc]:
+        def prepare_input(
+            texts: Iterable[Union[str, Doc]]
+        ) -> Iterable[Tuple[Union[str, bytes], _AnyContext]]:
+            # Serialize Doc inputs to bytes to avoid incurring pickling
+            # overhead when they are passed to child processes. Also yield
+            # any context objects they might have separately (as they are not serialized).
+            for doc_like in texts:
+                if isinstance(doc_like, Doc):
+                    yield (doc_like.to_bytes(), cast(_AnyContext, doc_like._context))
+                else:
+                    yield (doc_like, cast(_AnyContext, None))
+
+        serialized_texts_with_ctx = prepare_input(texts)  # type: ignore
         # raw_texts is used later to stop iteration.
-        texts, raw_texts = itertools.tee(texts)
+        texts, raw_texts = itertools.tee(serialized_texts_with_ctx)  # type: ignore
         # for sending texts to worker
         texts_q: List[mp.Queue] = [mp.Queue() for _ in range(n_process)]
         # for receiving byte-encoded docs from worker
@@ -1615,7 +1635,13 @@ class Language:
         procs = [
             mp.Process(
                 target=_apply_pipes,
-                args=(self._ensure_doc, pipes, rch, sch, Underscore.get_state()),
+                args=(
+                    self._ensure_doc_with_context,
+                    pipes,
+                    rch,
+                    sch,
+                    Underscore.get_state(),
+                ),
             )
             for rch, sch in zip(texts_q, bytedocs_send_ch)
         ]
@@ -1628,12 +1654,12 @@ class Language:
             recv.recv() for recv in cycle(bytedocs_recv_ch)
         )
         try:
-            for i, (_, (byte_doc, byte_context, byte_error)) in enumerate(
+            for i, (_, (byte_doc, context, byte_error)) in enumerate(
                 zip(raw_texts, byte_tuples), 1
             ):
                 if byte_doc is not None:
                     doc = Doc(self.vocab).from_bytes(byte_doc)
-                    doc._context = byte_context
+                    doc._context = context
                     yield doc
                 elif byte_error is not None:
                     error = srsly.msgpack_loads(byte_error)
@@ -1668,6 +1694,7 @@ class Language:
         *,
         vocab: Union[Vocab, bool] = True,
         disable: Iterable[str] = SimpleFrozenList(),
+        enable: Iterable[str] = SimpleFrozenList(),
         exclude: Iterable[str] = SimpleFrozenList(),
         meta: Dict[str, Any] = SimpleFrozenDict(),
         auto_fill: bool = True,
@@ -1682,6 +1709,8 @@ class Language:
         disable (Iterable[str]): Names of pipeline components to disable.
             Disabled pipes will be loaded but they won't be run unless you
             explicitly enable them by calling nlp.enable_pipe.
+        enable (Iterable[str]): Names of pipeline components to enable. All other
+            pipes will be disabled (and can be enabled using `nlp.enable_pipe`).
         exclude (Iterable[str]): Names of pipeline components to exclude.
             Excluded components won't be loaded.
         meta (Dict[str, Any]): Meta overrides for nlp.meta.
@@ -1835,8 +1864,15 @@ class Language:
         # Restore the original vocab after sourcing if necessary
         if vocab_b is not None:
             nlp.vocab.from_bytes(vocab_b)
-        disabled_pipes = [*config["nlp"]["disabled"], *disable]
+
+        # Resolve disabled/enabled settings.
+        disabled_pipes = cls._resolve_component_status(
+            [*config["nlp"]["disabled"], *disable],
+            [*config["nlp"].get("enabled", []), *enable],
+            config["nlp"]["pipeline"],
+        )
         nlp._disabled = set(p for p in disabled_pipes if p not in exclude)
+
         nlp.batch_size = config["nlp"]["batch_size"]
         nlp.config = filled if auto_fill else config
         if after_pipeline_creation is not None:
@@ -1988,6 +2024,42 @@ class Language:
         serializers["vocab"] = lambda p: self.vocab.to_disk(p, exclude=exclude)
         util.to_disk(path, serializers, exclude)
 
+    @staticmethod
+    def _resolve_component_status(
+        disable: Iterable[str], enable: Iterable[str], pipe_names: Collection[str]
+    ) -> Tuple[str, ...]:
+        """Derives whether (1) `disable` and `enable` values are consistent and (2)
+        resolves those to a single set of disabled components. Raises an error in
+        case of inconsistency.
+
+        disable (Iterable[str]): Names of components or serialization fields to disable.
+        enable (Iterable[str]): Names of pipeline components to enable.
+        pipe_names (Iterable[str]): Names of all pipeline components.
+
+        RETURNS (Tuple[str, ...]): Names of components to exclude from pipeline w.r.t.
+                                   specified includes and excludes.
+        """
+
+        if disable is not None and isinstance(disable, str):
+            disable = [disable]
+        to_disable = disable
+
+        if enable:
+            to_disable = [
+                pipe_name for pipe_name in pipe_names if pipe_name not in enable
+            ]
+            if disable and disable != to_disable:
+                raise ValueError(
+                    Errors.E1042.format(
+                        arg1="enable",
+                        arg2="disable",
+                        arg1_values=enable,
+                        arg2_values=disable,
+                    )
+                )
+
+        return tuple(to_disable)
+
     def from_disk(
         self,
         path: Union[str, Path],
@@ -2160,7 +2232,7 @@ def _copy_examples(examples: Iterable[Example]) -> List[Example]:
 
 
 def _apply_pipes(
-    ensure_doc: Callable[[Union[str, Doc]], Doc],
+    ensure_doc: Callable[[Union[str, Doc, bytes], _AnyContext], Doc],
     pipes: Iterable[Callable[..., Iterator[Doc]]],
     receiver,
     sender,
@@ -2181,17 +2253,19 @@ def _apply_pipes(
     Underscore.load_state(underscore_state)
     while True:
         try:
-            texts = receiver.get()
+            texts_with_ctx = receiver.get()
-            docs = (ensure_doc(text) for text in texts)
+            docs = (
+                ensure_doc(doc_like, context) for doc_like, context in texts_with_ctx
+            )
             for pipe in pipes:
                 docs = pipe(docs)  # type: ignore[arg-type, assignment]
             # Connection does not accept unpickable objects, so send list.
             byte_docs = [(doc.to_bytes(), doc._context, None) for doc in docs]
-            padding = [(None, None, None)] * (len(texts) - len(byte_docs))
+            padding = [(None, None, None)] * (len(texts_with_ctx) - len(byte_docs))
             sender.send(byte_docs + padding)  # type: ignore[operator]
         except Exception:
             error_msg = [(None, None, srsly.msgpack_dumps(traceback.format_exc()))]
-            padding = [(None, None, None)] * (len(texts) - 1)
+            padding = [(None, None, None)] * (len(texts_with_ctx) - 1)
             sender.send(error_msg + padding)
 
 

spacy/lookups.py

@@ -85,7 +85,7 @@ class Table(OrderedDict):
         value: The value to set.
         """
         key = get_string_id(key)
-        OrderedDict.__setitem__(self, key, value)
+        OrderedDict.__setitem__(self, key, value)  # type:ignore[assignment]
         self.bloom.add(key)
 
     def set(self, key: Union[str, int], value: Any) -> None:
@@ -104,7 +104,7 @@ class Table(OrderedDict):
         RETURNS: The value.
         """
         key = get_string_id(key)
-        return OrderedDict.__getitem__(self, key)
+        return OrderedDict.__getitem__(self, key)  # type:ignore[index]
 
     def get(self, key: Union[str, int], default: Optional[Any] = None) -> Any:
         """Get the value for a given key. String keys will be hashed.
@@ -114,7 +114,7 @@ class Table(OrderedDict):
         RETURNS: The value.
         """
         key = get_string_id(key)
-        return OrderedDict.get(self, key, default)
+        return OrderedDict.get(self, key, default)  # type:ignore[arg-type]
 
     def __contains__(self, key: Union[str, int]) -> bool:  # type: ignore[override]
         """Check whether a key is in the table. String keys will be hashed.

spacy/matcher/dependencymatcher.pyx

@@ -82,6 +82,10 @@ cdef class DependencyMatcher:
             "$-": self._imm_left_sib,
             "$++": self._right_sib,
             "$--": self._left_sib,
+            ">++": self._right_child,
+            ">--": self._left_child,
+            "<++": self._right_parent,
+            "<--": self._left_parent,
         }
 
     def __reduce__(self):
@@ -423,6 +427,22 @@ cdef class DependencyMatcher:
     def _left_sib(self, doc, node):
         return [doc[child.i] for child in doc[node].head.children if child.i < node]
 
+    def _right_child(self, doc, node):
+        return [doc[child.i] for child in doc[node].children if child.i > node]
+    
+    def _left_child(self, doc, node):
+        return [doc[child.i] for child in doc[node].children if child.i < node]
+
+    def _right_parent(self, doc, node):
+        if doc[node].head.i > node:
+            return [doc[node].head]
+        return []
+    
+    def _left_parent(self, doc, node):
+        if doc[node].head.i < node:
+            return [doc[node].head]
+        return []
+
     def _normalize_key(self, key):
         if isinstance(key, str):
             return self.vocab.strings.add(key)

spacy/matcher/matcher.pyx

@@ -90,6 +90,10 @@ cdef class Matcher:
         '?':      Make the pattern optional, by allowing it to match 0 or 1 times.
         '+':      Require the pattern to match 1 or more times.
         '*':      Allow the pattern to zero or more times.
+        '{n}':    Require the pattern to match exactly _n_ times.
+        '{n,m}':  Require the pattern to match at least _n_ but not more than _m_ times.
+        '{n,}':   Require the pattern to match at least _n_ times.
+        '{,m}':   Require the pattern to match at most _m_ times.
 
         The + and * operators return all possible matches (not just the greedy
         ones). However, the "greedy" argument can filter the final matches
@@ -786,6 +790,7 @@ def _preprocess_pattern(token_specs, vocab, extensions_table, extra_predicates):
 def _get_attr_values(spec, string_store):
     attr_values = []
     for attr, value in spec.items():
+        input_attr = attr
         if isinstance(attr, str):
             attr = attr.upper()
             if attr == '_':
@@ -814,7 +819,7 @@ def _get_attr_values(spec, string_store):
             attr_values.append((attr, value))
         else:
             # should be caught in validation
-            raise ValueError(Errors.E152.format(attr=attr))
+            raise ValueError(Errors.E152.format(attr=input_attr))
     return attr_values
 
 
@@ -1003,8 +1008,29 @@ def _get_operators(spec):
         return (ONE,)
     elif spec["OP"] in lookup:
         return lookup[spec["OP"]]
+    #Min_max {n,m}
+    elif spec["OP"].startswith("{") and spec["OP"].endswith("}"):
+        # {n}  --> {n,n}  exactly n                 ONE,(n)
+        # {n,m}--> {n,m}  min of n, max of m        ONE,(n),ZERO_ONE,(m)
+        # {,m} --> {0,m}  min of zero, max of m     ZERO_ONE,(m)
+        # {n,} --> {n,∞} min of n, max of inf       ONE,(n),ZERO_PLUS
+
+        min_max = spec["OP"][1:-1]
+        min_max = min_max if "," in min_max else f"{min_max},{min_max}"
+        n, m = min_max.split(",")
+
+        #1. Either n or m is a blank string and the other is numeric -->isdigit
+        #2. Both are numeric and n <= m
+        if (not n.isdecimal() and not m.isdecimal()) or (n.isdecimal() and m.isdecimal() and int(n) > int(m)):
+            keys = ", ".join(lookup.keys()) + ", {n}, {n,m}, {n,}, {,m} where n and m are integers and n <= m "
+            raise ValueError(Errors.E011.format(op=spec["OP"], opts=keys))
+
+        # if n is empty string, zero would be used
+        head = tuple(ONE for __ in range(int(n or 0)))
+        tail = tuple(ZERO_ONE for __ in range(int(m) - int(n or 0))) if m else (ZERO_PLUS,)
+        return head + tail
     else:
-        keys = ", ".join(lookup.keys())
+        keys = ", ".join(lookup.keys()) + ", {n}, {n,m}, {n,}, {,m} where n and m are integers and n <= m "
         raise ValueError(Errors.E011.format(op=spec["OP"], opts=keys))
 
 

spacy/matcher/phrasematcher.pyx

@@ -118,6 +118,8 @@ cdef class PhraseMatcher:
                     # if token is not found, break out of the loop
                     current_node = NULL
                     break
+            path_nodes.push_back(current_node)
+            path_keys.push_back(self._terminal_hash)
             # remove the tokens from trie node if there are no other
             # keywords with them
             result = map_get(current_node, self._terminal_hash)

spacy/ml/_precomputable_affine.py

@@ -22,9 +22,15 @@ def forward(model, X, is_train):
     nP = model.get_dim("nP")
     nI = model.get_dim("nI")
     W = model.get_param("W")
-    Yf = model.ops.gemm(X, W.reshape((nF * nO * nP, nI)), trans2=True)
+    # Preallocate array for layer output, including padding.
+    Yf = model.ops.alloc2f(X.shape[0] + 1, nF * nO * nP, zeros=False)
+    model.ops.gemm(X, W.reshape((nF * nO * nP, nI)), trans2=True, out=Yf[1:])
     Yf = Yf.reshape((Yf.shape[0], nF, nO, nP))
-    Yf = model.ops.xp.vstack((model.get_param("pad"), Yf))
+
+    # Set padding. Padding has shape (1, nF, nO, nP). Unfortunately, we cannot
+    # change its shape to (nF, nO, nP) without breaking existing models. So
+    # we'll squeeze the first dimension here.
+    Yf[0] = model.ops.xp.squeeze(model.get_param("pad"), 0)
 
     def backward(dY_ids):
         # This backprop is particularly tricky, because we get back a different

spacy/ml/callbacks.py

@@ -1,9 +1,14 @@
-from functools import partial
+from typing import Type, Callable, Dict, TYPE_CHECKING, List, Optional, Set
-from typing import Type, Callable, TYPE_CHECKING
+import functools
+import inspect
+import types
+import warnings
 
 from thinc.layers import with_nvtx_range
 from thinc.model import Model, wrap_model_recursive
+from thinc.util import use_nvtx_range
 
+from ..errors import Warnings
 from ..util import registry
 
 if TYPE_CHECKING:
@@ -11,29 +16,106 @@ if TYPE_CHECKING:
     from ..language import Language  # noqa: F401
 
 
-@registry.callbacks("spacy.models_with_nvtx_range.v1")
+DEFAULT_NVTX_ANNOTATABLE_PIPE_METHODS = [
-def create_models_with_nvtx_range(
+    "pipe",
-    forward_color: int = -1, backprop_color: int = -1
+    "predict",
-) -> Callable[["Language"], "Language"]:
+    "set_annotations",
-    def models_with_nvtx_range(nlp):
+    "update",
+    "rehearse",
+    "get_loss",
+    "initialize",
+    "begin_update",
+    "finish_update",
+    "update",
+]
+
+
+def models_with_nvtx_range(nlp, forward_color: int, backprop_color: int):
     pipes = [
         pipe
         for _, pipe in nlp.components
         if hasattr(pipe, "is_trainable") and pipe.is_trainable
     ]
 
-        # We need process all models jointly to avoid wrapping callbacks twice.
+    seen_models: Set[int] = set()
-        models = Model(
+    for pipe in pipes:
-            "wrap_with_nvtx_range",
+        for node in pipe.model.walk():
-            forward=lambda model, X, is_train: ...,
+            if id(node) in seen_models:
-            layers=[pipe.model for pipe in pipes],
+                continue
-        )
+            seen_models.add(id(node))
-
-        for node in models.walk():
             with_nvtx_range(
                 node, forward_color=forward_color, backprop_color=backprop_color
             )
 
     return nlp
 
-    return models_with_nvtx_range
+
+@registry.callbacks("spacy.models_with_nvtx_range.v1")
+def create_models_with_nvtx_range(
+    forward_color: int = -1, backprop_color: int = -1
+) -> Callable[["Language"], "Language"]:
+    return functools.partial(
+        models_with_nvtx_range,
+        forward_color=forward_color,
+        backprop_color=backprop_color,
+    )
+
+
+def nvtx_range_wrapper_for_pipe_method(self, func, *args, **kwargs):
+    if isinstance(func, functools.partial):
+        return func(*args, **kwargs)
+    else:
+        with use_nvtx_range(f"{self.name} {func.__name__}"):
+            return func(*args, **kwargs)
+
+
+def pipes_with_nvtx_range(
+    nlp, additional_pipe_functions: Optional[Dict[str, List[str]]]
+):
+    for _, pipe in nlp.components:
+        if additional_pipe_functions:
+            extra_funcs = additional_pipe_functions.get(pipe.name, [])
+        else:
+            extra_funcs = []
+
+        for name in DEFAULT_NVTX_ANNOTATABLE_PIPE_METHODS + extra_funcs:
+            func = getattr(pipe, name, None)
+            if func is None:
+                if name in extra_funcs:
+                    warnings.warn(Warnings.W121.format(method=name, pipe=pipe.name))
+                continue
+
+            wrapped_func = functools.partial(
+                types.MethodType(nvtx_range_wrapper_for_pipe_method, pipe), func
+            )
+
+            # Try to preserve the original function signature.
+            try:
+                wrapped_func.__signature__ = inspect.signature(func)  # type: ignore
+            except:
+                pass
+
+            try:
+                setattr(
+                    pipe,
+                    name,
+                    wrapped_func,
+                )
+            except AttributeError:
+                warnings.warn(Warnings.W122.format(method=name, pipe=pipe.name))
+
+    return nlp
+
+
+@registry.callbacks("spacy.models_and_pipes_with_nvtx_range.v1")
+def create_models_and_pipes_with_nvtx_range(
+    forward_color: int = -1,
+    backprop_color: int = -1,
+    additional_pipe_functions: Optional[Dict[str, List[str]]] = None,
+) -> Callable[["Language"], "Language"]:
+    def inner(nlp):
+        nlp = models_with_nvtx_range(nlp, forward_color, backprop_color)
+        nlp = pipes_with_nvtx_range(nlp, additional_pipe_functions)
+        return nlp
+
+    return inner

spacy/ml/models/entity_linker.py

@@ -23,7 +23,7 @@ def build_nel_encoder(
             ((tok2vec >> list2ragged()) & build_span_maker())
             >> extract_spans()
             >> reduce_mean()
-            >> residual(Maxout(nO=token_width, nI=token_width, nP=2, dropout=0.0))  # type: ignore[arg-type]
+            >> residual(Maxout(nO=token_width, nI=token_width, nP=2, dropout=0.0))  # type: ignore
             >> output_layer
         )
         model.set_ref("output_layer", output_layer)

spacy/ml/models/parser.py

@@ -72,7 +72,7 @@ def build_tb_parser_model(
     t2v_width = tok2vec.get_dim("nO") if tok2vec.has_dim("nO") else None
     tok2vec = chain(
         tok2vec,
-        cast(Model[List["Floats2d"], Floats2d], list2array()),
+        list2array(),
         Linear(hidden_width, t2v_width),
     )
     tok2vec.set_dim("nO", hidden_width)

spacy/ml/models/textcat.py

@@ -1,5 +1,5 @@
+from typing import Optional, List, cast
 from functools import partial
-from typing import Optional, List
 
 from thinc.types import Floats2d
 from thinc.api import Model, reduce_mean, Linear, list2ragged, Logistic
@@ -59,7 +59,8 @@ def build_simple_cnn_text_classifier(
             resizable_layer=resizable_layer,
         )
     model.set_ref("tok2vec", tok2vec)
-    model.set_dim("nO", nO)  # type: ignore  # TODO: remove type ignore once Thinc has been updated
+    if nO is not None:
+        model.set_dim("nO", cast(int, nO))
     model.attrs["multi_label"] = not exclusive_classes
     return model
 
@@ -85,7 +86,7 @@ def build_bow_text_classifier(
         if not no_output_layer:
             fill_defaults["b"] = NEG_VALUE
             output_layer = softmax_activation() if exclusive_classes else Logistic()
-        resizable_layer = resizable(  # type: ignore[var-annotated]
+        resizable_layer: Model[Floats2d, Floats2d] = resizable(
             sparse_linear,
             resize_layer=partial(resize_linear_weighted, fill_defaults=fill_defaults),
         )
@@ -93,7 +94,8 @@ def build_bow_text_classifier(
         model = with_cpu(model, model.ops)
         if output_layer:
             model = model >> with_cpu(output_layer, output_layer.ops)
-    model.set_dim("nO", nO)  # type: ignore[arg-type]
+    if nO is not None:
+        model.set_dim("nO", cast(int, nO))
     model.set_ref("output_layer", sparse_linear)
     model.attrs["multi_label"] = not exclusive_classes
     model.attrs["resize_output"] = partial(
@@ -129,8 +131,8 @@ def build_text_classifier_v2(
             output_layer = Linear(nO=nO, nI=nO_double) >> Logistic()
         model = (linear_model | cnn_model) >> output_layer
         model.set_ref("tok2vec", tok2vec)
-    if model.has_dim("nO") is not False:
+    if model.has_dim("nO") is not False and nO is not None:
-        model.set_dim("nO", nO)  # type: ignore[arg-type]
+        model.set_dim("nO", cast(int, nO))
     model.set_ref("output_layer", linear_model.get_ref("output_layer"))
     model.set_ref("attention_layer", attention_layer)
     model.set_ref("maxout_layer", maxout_layer)
@@ -164,7 +166,7 @@ def build_text_classifier_lowdata(
             >> list2ragged()
             >> ParametricAttention(width)
             >> reduce_sum()
-            >> residual(Relu(width, width)) ** 2  # type: ignore[arg-type]
+            >> residual(Relu(width, width)) ** 2
             >> Linear(nO, width)
         )
         if dropout:

spacy/ml/models/tok2vec.py

@@ -1,5 +1,5 @@
 from typing import Optional, List, Union, cast
-from thinc.types import Floats2d, Ints2d, Ragged
+from thinc.types import Floats2d, Ints2d, Ragged, Ints1d
 from thinc.api import chain, clone, concatenate, with_array, with_padded
 from thinc.api import Model, noop, list2ragged, ragged2list, HashEmbed
 from thinc.api import expand_window, residual, Maxout, Mish, PyTorchLSTM
@@ -159,7 +159,7 @@ def MultiHashEmbed(
     embeddings = [make_hash_embed(i) for i in range(len(attrs))]
     concat_size = width * (len(embeddings) + include_static_vectors)
     max_out: Model[Ragged, Ragged] = with_array(
-        Maxout(width, concat_size, nP=3, dropout=0.0, normalize=True)  # type: ignore
+        Maxout(width, concat_size, nP=3, dropout=0.0, normalize=True)
     )
     if include_static_vectors:
         feature_extractor: Model[List[Doc], Ragged] = chain(
@@ -173,7 +173,7 @@ def MultiHashEmbed(
                 StaticVectors(width, dropout=0.0),
             ),
             max_out,
-            cast(Model[Ragged, List[Floats2d]], ragged2list()),
+            ragged2list(),
         )
     else:
         model = chain(
@@ -181,7 +181,7 @@ def MultiHashEmbed(
             cast(Model[List[Ints2d], Ragged], list2ragged()),
             with_array(concatenate(*embeddings)),
             max_out,
-            cast(Model[Ragged, List[Floats2d]], ragged2list()),
+            ragged2list(),
         )
     return model
 
@@ -232,12 +232,12 @@ def CharacterEmbed(
     feature_extractor: Model[List[Doc], Ragged] = chain(
         FeatureExtractor([feature]),
         cast(Model[List[Ints2d], Ragged], list2ragged()),
-        with_array(HashEmbed(nO=width, nV=rows, column=0, seed=5)),  # type: ignore
+        with_array(HashEmbed(nO=width, nV=rows, column=0, seed=5)),  # type: ignore[misc]
     )
     max_out: Model[Ragged, Ragged]
     if include_static_vectors:
         max_out = with_array(
-            Maxout(width, nM * nC + (2 * width), nP=3, normalize=True, dropout=0.0)  # type: ignore
+            Maxout(width, nM * nC + (2 * width), nP=3, normalize=True, dropout=0.0)
         )
         model = chain(
             concatenate(
@@ -246,11 +246,11 @@ def CharacterEmbed(
                 StaticVectors(width, dropout=0.0),
             ),
             max_out,
-            cast(Model[Ragged, List[Floats2d]], ragged2list()),
+            ragged2list(),
         )
     else:
         max_out = with_array(
-            Maxout(width, nM * nC + width, nP=3, normalize=True, dropout=0.0)  # type: ignore
+            Maxout(width, nM * nC + width, nP=3, normalize=True, dropout=0.0)
         )
         model = chain(
             concatenate(
@@ -258,7 +258,7 @@ def CharacterEmbed(
                 feature_extractor,
             ),
             max_out,
-            cast(Model[Ragged, List[Floats2d]], ragged2list()),
+            ragged2list(),
         )
     return model
 
@@ -289,10 +289,10 @@ def MaxoutWindowEncoder(
             normalize=True,
         ),
     )
-    model = clone(residual(cnn), depth)  # type: ignore[arg-type]
+    model = clone(residual(cnn), depth)
     model.set_dim("nO", width)
     receptive_field = window_size * depth
-    return with_array(model, pad=receptive_field)  # type: ignore[arg-type]
+    return with_array(model, pad=receptive_field)
 
 
 @registry.architectures("spacy.MishWindowEncoder.v2")
@@ -313,9 +313,9 @@ def MishWindowEncoder(
         expand_window(window_size=window_size),
         Mish(nO=width, nI=width * ((window_size * 2) + 1), dropout=0.0, normalize=True),
     )
-    model = clone(residual(cnn), depth)  # type: ignore[arg-type]
+    model = clone(residual(cnn), depth)
     model.set_dim("nO", width)
-    return with_array(model)  # type: ignore[arg-type]
+    return with_array(model)
 
 
 @registry.architectures("spacy.TorchBiLSTMEncoder.v1")

spacy/ml/parser_model.pxd

@@ -1,4 +1,5 @@
 from libc.string cimport memset, memcpy
+from thinc.backends.cblas cimport CBlas
 from ..typedefs cimport weight_t, hash_t
 from ..pipeline._parser_internals._state cimport StateC
 
@@ -38,7 +39,7 @@ cdef ActivationsC alloc_activations(SizesC n) nogil
 
 cdef void free_activations(const ActivationsC* A) nogil
 
-cdef void predict_states(ActivationsC* A, StateC** states,
+cdef void predict_states(CBlas cblas, ActivationsC* A, StateC** states,
         const WeightsC* W, SizesC n) nogil
  
 cdef int arg_max_if_valid(const weight_t* scores, const int* is_valid, int n) nogil

spacy/ml/parser_model.pyx

@@ -4,11 +4,11 @@ from libc.math cimport exp
 from libc.string cimport memset, memcpy
 from libc.stdlib cimport calloc, free, realloc
 from thinc.backends.linalg cimport Vec, VecVec
-cimport blis.cy
+from thinc.backends.cblas cimport saxpy, sgemm
 
 import numpy
 import numpy.random
-from thinc.api import Model, CupyOps, NumpyOps
+from thinc.api import Model, CupyOps, NumpyOps, get_ops
 
 from .. import util
 from ..errors import Errors
@@ -91,7 +91,7 @@ cdef void resize_activations(ActivationsC* A, SizesC n) nogil:
     A._curr_size = n.states
 
 
-cdef void predict_states(ActivationsC* A, StateC** states,
+cdef void predict_states(CBlas cblas, ActivationsC* A, StateC** states,
         const WeightsC* W, SizesC n) nogil:
     cdef double one = 1.0
     resize_activations(A, n)
@@ -99,7 +99,7 @@ cdef void predict_states(ActivationsC* A, StateC** states,
         states[i].set_context_tokens(&A.token_ids[i*n.feats], n.feats)
     memset(A.unmaxed, 0, n.states * n.hiddens * n.pieces * sizeof(float))
     memset(A.hiddens, 0, n.states * n.hiddens * sizeof(float))
-    sum_state_features(A.unmaxed,
+    sum_state_features(cblas, A.unmaxed,
         W.feat_weights, A.token_ids, n.states, n.feats, n.hiddens * n.pieces)
     for i in range(n.states):
         VecVec.add_i(&A.unmaxed[i*n.hiddens*n.pieces],
@@ -113,12 +113,10 @@ cdef void predict_states(ActivationsC* A, StateC** states,
         memcpy(A.scores, A.hiddens, n.states * n.classes * sizeof(float))
     else:
         # Compute hidden-to-output
-        blis.cy.gemm(blis.cy.NO_TRANSPOSE, blis.cy.TRANSPOSE,
+        sgemm(cblas)(False, True, n.states, n.classes, n.hiddens,
-            n.states, n.classes, n.hiddens, one,
+            1.0, <const float *>A.hiddens, n.hiddens,
-            <float*>A.hiddens, n.hiddens, 1,
+            <const float *>W.hidden_weights, n.hiddens,
-            <float*>W.hidden_weights, n.hiddens, 1,
+            0.0, A.scores, n.classes)
-            one,
-            <float*>A.scores, n.classes, 1)
         # Add bias
         for i in range(n.states):
             VecVec.add_i(&A.scores[i*n.classes],
@@ -135,7 +133,7 @@ cdef void predict_states(ActivationsC* A, StateC** states,
                 A.scores[i*n.classes+j] = min_
 
 
-cdef void sum_state_features(float* output,
+cdef void sum_state_features(CBlas cblas, float* output,
         const float* cached, const int* token_ids, int B, int F, int O) nogil:
     cdef int idx, b, f, i
     cdef const float* feature
@@ -150,9 +148,7 @@ cdef void sum_state_features(float* output,
             else:
                 idx = token_ids[f] * id_stride + f*O
                 feature = &cached[idx]
-            blis.cy.axpyv(blis.cy.NO_CONJUGATE, O, one,
+            saxpy(cblas)(O, one, <const float*>feature, 1, &output[b*O], 1)
-                <float*>feature, 1,
-                &output[b*O], 1)
         token_ids += F
 
 
@@ -443,9 +439,15 @@ cdef class precompute_hiddens:
         # - Output from backward on GPU
         bp_hiddens = self._bp_hiddens
 
+        cdef CBlas cblas
+        if isinstance(self.ops, CupyOps):
+            cblas = NUMPY_OPS.cblas()
+        else:
+            cblas = self.ops.cblas()
+
         feat_weights = self.get_feat_weights()
         cdef int[:, ::1] ids = token_ids
-        sum_state_features(<float*>state_vector.data,
+        sum_state_features(cblas, <float*>state_vector.data,
             feat_weights, &ids[0,0],
             token_ids.shape[0], self.nF, self.nO*self.nP)
         state_vector += self.bias

spacy/ml/staticvectors.py

@@ -40,17 +40,15 @@ def forward(
     if not token_count:
         return _handle_empty(model.ops, model.get_dim("nO"))
     key_attr: int = model.attrs["key_attr"]
-    keys: Ints1d = model.ops.flatten(
+    keys = model.ops.flatten([cast(Ints1d, doc.to_array(key_attr)) for doc in docs])
-        cast(Sequence, [doc.to_array(key_attr) for doc in docs])
-    )
     vocab: Vocab = docs[0].vocab
     W = cast(Floats2d, model.ops.as_contig(model.get_param("W")))
     if vocab.vectors.mode == Mode.default:
-        V = cast(Floats2d, model.ops.asarray(vocab.vectors.data))
+        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:
-        V = cast(Floats2d, vocab.vectors.get_batch(keys))
+        V = vocab.vectors.get_batch(keys)
         V = model.ops.as_contig(V)
     else:
         raise RuntimeError(Errors.E896)
@@ -62,9 +60,7 @@ def forward(
         # Convert negative indices to 0-vectors
         # TODO: more options for UNK tokens
         vectors_data[rows < 0] = 0
-    output = Ragged(
+    output = Ragged(vectors_data, model.ops.asarray1i([len(doc) for doc in docs]))
-        vectors_data, model.ops.asarray([len(doc) for doc in docs], dtype="i")  # type: ignore
-    )
     mask = None
     if is_train:
         mask = _get_drop_mask(model.ops, W.shape[0], model.attrs.get("dropout_rate"))
@@ -77,7 +73,9 @@ def forward(
         model.inc_grad(
             "W",
             model.ops.gemm(
-                cast(Floats2d, d_output.data), model.ops.as_contig(V), trans1=True
+                cast(Floats2d, d_output.data),
+                cast(Floats2d, model.ops.as_contig(V)),
+                trans1=True,
             ),
         )
         return []

spacy/pipeline/__init__.py

@@ -13,6 +13,7 @@ from .sentencizer import Sentencizer
 from .tagger import Tagger
 from .textcat import TextCategorizer
 from .spancat import SpanCategorizer
+from .span_ruler import SpanRuler
 from .textcat_multilabel import MultiLabel_TextCategorizer
 from .tok2vec import Tok2Vec
 from .functions import merge_entities, merge_noun_chunks, merge_subtokens
@@ -30,6 +31,7 @@ __all__ = [
     "SentenceRecognizer",
     "Sentencizer",
     "SpanCategorizer",
+    "SpanRuler",
     "Tagger",
     "TextCategorizer",
     "Tok2Vec",

spacy/pipeline/_parser_internals/arc_eager.pyx

@@ -10,6 +10,7 @@ from ...strings cimport hash_string
 from ...structs cimport TokenC
 from ...tokens.doc cimport Doc, set_children_from_heads
 from ...tokens.token cimport MISSING_DEP
+from ...training import split_bilu_label
 from ...training.example cimport Example
 from .stateclass cimport StateClass
 from ._state cimport StateC, ArcC
@@ -687,7 +688,7 @@ cdef class ArcEager(TransitionSystem):
             return self.c[name_or_id]
         name = name_or_id
         if '-' in name:
-            move_str, label_str = name.split('-', 1)
+            move_str, label_str = split_bilu_label(name)
             label = self.strings[label_str]
         else:
             move_str = name

spacy/pipeline/_parser_internals/ner.pyx

@@ -13,6 +13,7 @@ from ...typedefs cimport weight_t, attr_t
 from ...lexeme cimport Lexeme
 from ...attrs cimport IS_SPACE
 from ...structs cimport TokenC, SpanC
+from ...training import split_bilu_label
 from ...training.example cimport Example
 from .stateclass cimport StateClass
 from ._state cimport StateC
@@ -182,7 +183,7 @@ cdef class BiluoPushDown(TransitionSystem):
         if name == '-' or name == '' or name is None:
             return Transition(clas=0, move=MISSING, label=0, score=0)
         elif '-' in name:
-            move_str, label_str = name.split('-', 1)
+            move_str, label_str = split_bilu_label(name)
             # Deprecated, hacky way to denote 'not this entity'
             if label_str.startswith('!'):
                 raise ValueError(Errors.E869.format(label=name))

spacy/pipeline/_parser_internals/nonproj.hh

@@ -0,0 +1,11 @@
+#ifndef NONPROJ_HH
+#define NONPROJ_HH
+
+#include <stdexcept>
+#include <string>
+
+void raise_domain_error(std::string const &msg) {
+    throw std::domain_error(msg);
+}
+
+#endif // NONPROJ_HH

spacy/pipeline/_parser_internals/nonproj.pxd

@@ -0,0 +1,4 @@
+from libcpp.string cimport string
+
+cdef extern from "nonproj.hh":
+    cdef void raise_domain_error(const string& msg) nogil except +

spacy/pipeline/_parser_internals/nonproj.pyx

@@ -4,10 +4,13 @@ for doing pseudo-projective parsing implementation uses the HEAD decoration
 scheme.
 """
 from copy import copy
+from cython.operator cimport preincrement as incr, dereference as deref
 from libc.limits cimport INT_MAX
 from libc.stdlib cimport abs
 from libcpp cimport bool
+from libcpp.string cimport string, to_string
 from libcpp.vector cimport vector
+from libcpp.unordered_set cimport unordered_set
 
 from ...tokens.doc cimport Doc, set_children_from_heads
 
@@ -49,7 +52,7 @@ def is_nonproj_arc(tokenid, heads):
     return _is_nonproj_arc(tokenid, c_heads)
 
 
-cdef bool _is_nonproj_arc(int tokenid, const vector[int]& heads) nogil:
+cdef bool _is_nonproj_arc(int tokenid, const vector[int]& heads) nogil except *:
     # definition (e.g. Havelka 2007): an arc h -> d, h < d is non-projective
     # if there is a token k, h < k < d such that h is not
     # an ancestor of k. Same for h -> d, h > d
@@ -65,25 +68,49 @@ cdef bool _is_nonproj_arc(int tokenid, const vector[int]& heads) nogil:
     else:
         start, end = (tokenid+1, head)
     for k in range(start, end):
-        if _has_head_as_ancestor(k, head, heads):
+        if not _has_head_as_ancestor(k, head, heads):
-            continue
-        else:  # head not in ancestors: d -> h is non-projective
             return True
     return False
 
 
-cdef bool _has_head_as_ancestor(int tokenid, int head, const vector[int]& heads) nogil:
+cdef bool _has_head_as_ancestor(int tokenid, int head, const vector[int]& heads) nogil except *:
     ancestor = tokenid
-    cnt = 0
+    cdef unordered_set[int] seen_tokens
-    while cnt < heads.size():
+    seen_tokens.insert(ancestor)
+    while True:
+        # Reached the head or a disconnected node
         if heads[ancestor] == head or heads[ancestor] < 0:
             return True
+        # Reached the root
+        if heads[ancestor] == ancestor:
+            return False
         ancestor = heads[ancestor]
-        cnt += 1
+        result = seen_tokens.insert(ancestor)
+        # Found cycle
+        if not result.second:
+            raise_domain_error(heads_to_string(heads))
 
     return False
 
 
+cdef string heads_to_string(const vector[int]& heads) nogil:
+    cdef vector[int].const_iterator citer
+    cdef string cycle_str
+
+    cycle_str.append("Found cycle in dependency graph: [")
+
+    # FIXME: Rewrite using ostringstream when available in Cython.
+    citer = heads.const_begin()
+    while citer != heads.const_end():
+        if citer != heads.const_begin():
+            cycle_str.append(", ")
+        cycle_str.append(to_string(deref(citer)))
+        incr(citer)
+    cycle_str.append("]")
+
+    return cycle_str
+
+
 def is_nonproj_tree(heads):
     cdef vector[int] c_heads = _heads_to_c(heads)
     # a tree is non-projective if at least one arc is non-projective
@@ -176,11 +203,12 @@ def get_smallest_nonproj_arc_slow(heads):
     return _get_smallest_nonproj_arc(c_heads)
 
 
-cdef int _get_smallest_nonproj_arc(const vector[int]& heads) nogil:
+cdef int _get_smallest_nonproj_arc(const vector[int]& heads) nogil except -2:
     # return the smallest non-proj arc or None
     # where size is defined as the distance between dep and head
     # and ties are broken left to right
     cdef int smallest_size = INT_MAX
+    # -1 means its already projective.
     cdef int smallest_np_arc = -1
     cdef int size
     cdef int tokenid

spacy/pipeline/dep_parser.pyx

@@ -12,6 +12,7 @@ from ..language import Language
 from ._parser_internals import nonproj
 from ._parser_internals.nonproj import DELIMITER
 from ..scorer import Scorer
+from ..training import remove_bilu_prefix
 from ..util import registry
 
 
@@ -314,7 +315,7 @@ cdef class DependencyParser(Parser):
         # Get the labels from the model by looking at the available moves
         for move in self.move_names:
             if "-" in move:
-                label = move.split("-")[1]
+                label = remove_bilu_prefix(move)
                 if DELIMITER in label:
                     label = label.split(DELIMITER)[1]
                 labels.add(label)

spacy/pipeline/edit_tree_lemmatizer.py

@@ -138,7 +138,7 @@ class EditTreeLemmatizer(TrainablePipe):
 
             truths.append(eg_truths)
 
-        d_scores, loss = loss_func(scores, truths)  # type: ignore
+        d_scores, loss = loss_func(scores, truths)
         if self.model.ops.xp.isnan(loss):
             raise ValueError(Errors.E910.format(name=self.name))
 

spacy/pipeline/entity_linker.py

@@ -56,6 +56,7 @@ DEFAULT_NEL_MODEL = Config().from_str(default_model_config)["model"]
         "overwrite": True,
         "scorer": {"@scorers": "spacy.entity_linker_scorer.v1"},
         "use_gold_ents": True,
+        "threshold": None,
     },
     default_score_weights={
         "nel_micro_f": 1.0,
@@ -77,6 +78,7 @@ def make_entity_linker(
     overwrite: bool,
     scorer: Optional[Callable],
     use_gold_ents: bool,
+    threshold: Optional[float] = None,
 ):
     """Construct an EntityLinker component.
 
@@ -91,6 +93,10 @@ def make_entity_linker(
     get_candidates (Callable[[KnowledgeBase, "Span"], Iterable[Candidate]]): Function that
         produces a list of candidates, given a certain knowledge base and a textual mention.
     scorer (Optional[Callable]): The scoring method.
+    use_gold_ents (bool): Whether to copy entities from gold docs or not. If false, another
+        component must provide entity annotations.
+    threshold (Optional[float]): Confidence threshold for entity predictions. If confidence is below the threshold,
+        prediction is discarded. If None, predictions are not filtered by any threshold.
     """
 
     if not model.attrs.get("include_span_maker", False):
@@ -121,6 +127,7 @@ def make_entity_linker(
         overwrite=overwrite,
         scorer=scorer,
         use_gold_ents=use_gold_ents,
+        threshold=threshold,
     )
 
 
@@ -156,6 +163,7 @@ class EntityLinker(TrainablePipe):
         overwrite: bool = BACKWARD_OVERWRITE,
         scorer: Optional[Callable] = entity_linker_score,
         use_gold_ents: bool,
+        threshold: Optional[float] = None,
     ) -> None:
         """Initialize an entity linker.
 
@@ -174,9 +182,20 @@ class EntityLinker(TrainablePipe):
             Scorer.score_links.
         use_gold_ents (bool): Whether to copy entities from gold docs or not. If false, another
             component must provide entity annotations.
-
+        threshold (Optional[float]): Confidence threshold for entity predictions. If confidence is below the
+            threshold, prediction is discarded. If None, predictions are not filtered by any threshold.
         DOCS: https://spacy.io/api/entitylinker#init
         """
+
+        if threshold is not None and not (0 <= threshold <= 1):
+            raise ValueError(
+                Errors.E1043.format(
+                    range_start=0,
+                    range_end=1,
+                    value=threshold,
+                )
+            )
+
         self.vocab = vocab
         self.model = model
         self.name = name
@@ -192,6 +211,7 @@ class EntityLinker(TrainablePipe):
         self.kb = empty_kb(entity_vector_length)(self.vocab)
         self.scorer = scorer
         self.use_gold_ents = use_gold_ents
+        self.threshold = threshold
 
     def set_kb(self, kb_loader: Callable[[Vocab], KnowledgeBase]):
         """Define the KB of this pipe by providing a function that will
@@ -234,10 +254,11 @@ class EntityLinker(TrainablePipe):
         nO = self.kb.entity_vector_length
         doc_sample = []
         vector_sample = []
-        for example in islice(get_examples(), 10):
+        for eg in islice(get_examples(), 10):
-            doc = example.x
+            doc = eg.x
             if self.use_gold_ents:
-                doc.ents = example.y.ents
+                ents, _ = eg.get_aligned_ents_and_ner()
+                doc.ents = ents
             doc_sample.append(doc)
             vector_sample.append(self.model.ops.alloc1f(nO))
         assert len(doc_sample) > 0, Errors.E923.format(name=self.name)
@@ -312,7 +333,8 @@ class EntityLinker(TrainablePipe):
 
         for doc, ex in zip(docs, examples):
             if self.use_gold_ents:
-                doc.ents = ex.reference.ents
+                ents, _ = ex.get_aligned_ents_and_ner()
+                doc.ents = ents
             else:
                 # only keep matching ents
                 doc.ents = ex.get_matching_ents()
@@ -345,7 +367,7 @@ class EntityLinker(TrainablePipe):
         for eg in examples:
             kb_ids = eg.get_aligned("ENT_KB_ID", as_string=True)
 
-            for ent in eg.reference.ents:
+            for ent in eg.get_matching_ents():
                 kb_id = kb_ids[ent.start]
                 if kb_id:
                     entity_encoding = self.kb.get_vector(kb_id)
@@ -353,22 +375,25 @@ class EntityLinker(TrainablePipe):
                     keep_ents.append(eidx)
 
                 eidx += 1
-        entity_encodings = self.model.ops.asarray(entity_encodings, dtype="float32")
+        entity_encodings = self.model.ops.asarray2f(entity_encodings, dtype="float32")
         selected_encodings = sentence_encodings[keep_ents]
 
-        # If the entity encodings list is empty, then
+        # if there are no matches, short circuit
+        if not keep_ents:
+            out = self.model.ops.alloc2f(*sentence_encodings.shape)
+            return 0, out
+
         if selected_encodings.shape != entity_encodings.shape:
             err = Errors.E147.format(
                 method="get_loss", msg="gold entities do not match up"
             )
             raise RuntimeError(err)
-        # TODO: fix typing issue here
+        gradients = self.distance.get_grad(selected_encodings, entity_encodings)
-        gradients = self.distance.get_grad(selected_encodings, entity_encodings)  # type: ignore
         # to match the input size, we need to give a zero gradient for items not in the kb
         out = self.model.ops.alloc2f(*sentence_encodings.shape)
         out[keep_ents] = gradients
 
-        loss = self.distance.get_loss(selected_encodings, entity_encodings)  # type: ignore
+        loss = self.distance.get_loss(selected_encodings, entity_encodings)
         loss = loss / len(entity_encodings)
         return float(loss), out
 
@@ -385,18 +410,21 @@ class EntityLinker(TrainablePipe):
         self.validate_kb()
         entity_count = 0
         final_kb_ids: List[str] = []
+        xp = self.model.ops.xp
         if not docs:
             return final_kb_ids
         if isinstance(docs, Doc):
             docs = [docs]
         for i, doc in enumerate(docs):
+            if len(doc) == 0:
+                continue
             sentences = [s for s in doc.sents]
-            if len(doc) > 0:
             # Looping through each entity (TODO: rewrite)
             for ent in doc.ents:
-                    sent = ent.sent
+                sent_index = sentences.index(ent.sent)
-                    sent_index = sentences.index(sent)
                 assert sent_index >= 0
+
+                if self.incl_context:
                     # get n_neighbour sentences, clipped to the length of the document
                     start_sentence = max(0, sent_index - self.n_sents)
                     end_sentence = min(len(sentences) - 1, sent_index + self.n_sents)
@@ -404,8 +432,6 @@ class EntityLinker(TrainablePipe):
                     end_token = sentences[end_sentence].end
                     sent_doc = doc[start_token:end_token].as_doc()
                     # currently, the context is the same for each entity in a sentence (should be refined)
-                    xp = self.model.ops.xp
-                    if self.incl_context:
                     sentence_encoding = self.model.predict([sent_doc])[0]
                     sentence_encoding_t = sentence_encoding.T
                     sentence_norm = xp.linalg.norm(sentence_encoding_t)
@@ -418,9 +444,8 @@ class EntityLinker(TrainablePipe):
                     if not candidates:
                         # no prediction possible for this entity - setting to NIL
                         final_kb_ids.append(self.NIL)
-                        elif len(candidates) == 1:
+                    elif len(candidates) == 1 and self.threshold is None:
                         # shortcut for efficiency reasons: take the 1 candidate
-                            # TODO: thresholding
                         final_kb_ids.append(candidates[0].entity_)
                     else:
                         random.shuffle(candidates)
@@ -449,10 +474,11 @@ class EntityLinker(TrainablePipe):
                             if sims.shape != prior_probs.shape:
                                 raise ValueError(Errors.E161)
                             scores = prior_probs + sims - (prior_probs * sims)
-                            # TODO: thresholding
+                        final_kb_ids.append(
-                            best_index = scores.argmax().item()
+                            candidates[scores.argmax().item()].entity_
-                            best_candidate = candidates[best_index]
+                            if self.threshold is None or scores.max() >= self.threshold
-                            final_kb_ids.append(best_candidate.entity_)
+                            else EntityLinker.NIL
+                        )
         if not (len(final_kb_ids) == entity_count):
             err = Errors.E147.format(
                 method="predict", msg="result variables not of equal length"

spacy/pipeline/entityruler.py

@@ -159,10 +159,8 @@ class EntityRuler(Pipe):
         self._require_patterns()
         with warnings.catch_warnings():
             warnings.filterwarnings("ignore", message="\\[W036")
-            matches = cast(
+            matches = list(self.matcher(doc)) + list(self.phrase_matcher(doc))
-                List[Tuple[int, int, int]],
+
-                list(self.matcher(doc)) + list(self.phrase_matcher(doc)),
-            )
         final_matches = set(
             [(m_id, start, end) for m_id, start, end in matches if start != end]
         )
@@ -182,10 +180,7 @@ class EntityRuler(Pipe):
             if start not in seen_tokens and end - 1 not in seen_tokens:
                 if match_id in self._ent_ids:
                     label, ent_id = self._ent_ids[match_id]
-                    span = Span(doc, start, end, label=label)
+                    span = Span(doc, start, end, label=label, span_id=ent_id)
-                    if ent_id:
-                        for token in span:
-                            token.ent_id_ = ent_id
                 else:
                     span = Span(doc, start, end, label=match_id)
                 new_entities.append(span)
@@ -359,7 +354,9 @@ class EntityRuler(Pipe):
             (label, eid) for (label, eid) in self._ent_ids.values() if eid == ent_id
         ]
         if not label_id_pairs:
-            raise ValueError(Errors.E1024.format(ent_id=ent_id))
+            raise ValueError(
+                Errors.E1024.format(attr_type="ID", label=ent_id, component=self.name)
+            )
         created_labels = [
             self._create_label(label, eid) for (label, eid) in label_id_pairs
         ]

spacy/pipeline/legacy/entity_linker.py

@@ -7,7 +7,7 @@ from pathlib import Path
 from itertools import islice
 import srsly
 import random
-from thinc.api import CosineDistance, Model, Optimizer, Config
+from thinc.api import CosineDistance, Model, Optimizer
 from thinc.api import set_dropout_rate
 import warnings
 
@@ -20,7 +20,7 @@ from ...language import Language
 from ...vocab import Vocab
 from ...training import Example, validate_examples, validate_get_examples
 from ...errors import Errors, Warnings
-from ...util import SimpleFrozenList, registry
+from ...util import SimpleFrozenList
 from ... import util
 from ...scorer import Scorer
 
@@ -70,7 +70,6 @@ class EntityLinker_v1(TrainablePipe):
             produces a list of candidates, given a certain knowledge base and a textual mention.
         scorer (Optional[Callable]): The scoring method. Defaults to
             Scorer.score_links.
-
         DOCS: https://spacy.io/api/entitylinker#init
         """
         self.vocab = vocab
@@ -213,15 +212,14 @@ class EntityLinker_v1(TrainablePipe):
                 if kb_id:
                     entity_encoding = self.kb.get_vector(kb_id)
                     entity_encodings.append(entity_encoding)
-        entity_encodings = self.model.ops.asarray(entity_encodings, dtype="float32")
+        entity_encodings = self.model.ops.asarray2f(entity_encodings)
         if sentence_encodings.shape != entity_encodings.shape:
             err = Errors.E147.format(
                 method="get_loss", msg="gold entities do not match up"
             )
             raise RuntimeError(err)
-        # TODO: fix typing issue here
+        gradients = self.distance.get_grad(sentence_encodings, entity_encodings)
-        gradients = self.distance.get_grad(sentence_encodings, entity_encodings)  # type: ignore
+        loss = self.distance.get_loss(sentence_encodings, entity_encodings)
-        loss = self.distance.get_loss(sentence_encodings, entity_encodings)  # type: ignore
         loss = loss / len(entity_encodings)
         return float(loss), gradients
 
@@ -273,7 +271,6 @@ class EntityLinker_v1(TrainablePipe):
                             final_kb_ids.append(self.NIL)
                         elif len(candidates) == 1:
                             # shortcut for efficiency reasons: take the 1 candidate
-                            # TODO: thresholding
                             final_kb_ids.append(candidates[0].entity_)
                         else:
                             random.shuffle(candidates)
@@ -302,7 +299,6 @@ class EntityLinker_v1(TrainablePipe):
                                 if sims.shape != prior_probs.shape:
                                     raise ValueError(Errors.E161)
                                 scores = prior_probs + sims - (prior_probs * sims)
-                            # TODO: thresholding
                             best_index = scores.argmax().item()
                             best_candidate = candidates[best_index]
                             final_kb_ids.append(best_candidate.entity_)

spacy/pipeline/ner.pyx

@@ -6,10 +6,10 @@ from thinc.api import Model, Config
 from ._parser_internals.transition_system import TransitionSystem
 from .transition_parser cimport Parser
 from ._parser_internals.ner cimport BiluoPushDown
-
 from ..language import Language
 from ..scorer import get_ner_prf, PRFScore
 from ..util import registry
+from ..training import remove_bilu_prefix
 
 
 default_model_config = """
@@ -242,7 +242,7 @@ cdef class EntityRecognizer(Parser):
     def labels(self):
         # Get the labels from the model by looking at the available moves, e.g.
         # B-PERSON, I-PERSON, L-PERSON, U-PERSON
-        labels = set(move.split("-")[1] for move in self.move_names
+        labels = set(remove_bilu_prefix(move) for move in self.move_names
                      if move[0] in ("B", "I", "L", "U"))
         return tuple(sorted(labels))
 

spacy/pipeline/pipe.pyx

@@ -31,7 +31,7 @@ cdef class Pipe:
         and returned. This usually happens under the hood when the nlp object
         is called on a text and all components are applied to the Doc.
 
-        docs (Doc): The Doc to process.
+        doc (Doc): The Doc to process.
         RETURNS (Doc): The processed Doc.
 
         DOCS: https://spacy.io/api/pipe#call

spacy/pipeline/span_ruler.py

@@ -0,0 +1,569 @@
+from typing import Optional, Union, List, Dict, Tuple, Iterable, Any, Callable
+from typing import Sequence, Set, cast
+import warnings
+from functools import partial
+from pathlib import Path
+import srsly
+
+from .pipe import Pipe
+from ..training import Example
+from ..language import Language
+from ..errors import Errors, Warnings
+from ..util import ensure_path, SimpleFrozenList, registry
+from ..tokens import Doc, Span
+from ..scorer import Scorer
+from ..matcher import Matcher, PhraseMatcher
+from .. import util
+
+PatternType = Dict[str, Union[str, List[Dict[str, Any]]]]
+DEFAULT_SPANS_KEY = "ruler"
+
+
+@Language.factory(
+    "future_entity_ruler",
+    assigns=["doc.ents"],
+    default_config={
+        "phrase_matcher_attr": None,
+        "validate": False,
+        "overwrite_ents": False,
+        "scorer": {"@scorers": "spacy.entity_ruler_scorer.v1"},
+        "ent_id_sep": "__unused__",
+    },
+    default_score_weights={
+        "ents_f": 1.0,
+        "ents_p": 0.0,
+        "ents_r": 0.0,
+        "ents_per_type": None,
+    },
+)
+def make_entity_ruler(
+    nlp: Language,
+    name: str,
+    phrase_matcher_attr: Optional[Union[int, str]],
+    validate: bool,
+    overwrite_ents: bool,
+    scorer: Optional[Callable],
+    ent_id_sep: str,
+):
+    if overwrite_ents:
+        ents_filter = prioritize_new_ents_filter
+    else:
+        ents_filter = prioritize_existing_ents_filter
+    return SpanRuler(
+        nlp,
+        name,
+        spans_key=None,
+        spans_filter=None,
+        annotate_ents=True,
+        ents_filter=ents_filter,
+        phrase_matcher_attr=phrase_matcher_attr,
+        validate=validate,
+        overwrite=False,
+        scorer=scorer,
+    )
+
+
+@Language.factory(
+    "span_ruler",
+    assigns=["doc.spans"],
+    default_config={
+        "spans_key": DEFAULT_SPANS_KEY,
+        "spans_filter": None,
+        "annotate_ents": False,
+        "ents_filter": {"@misc": "spacy.first_longest_spans_filter.v1"},
+        "phrase_matcher_attr": None,
+        "validate": False,
+        "overwrite": True,
+        "scorer": {
+            "@scorers": "spacy.overlapping_labeled_spans_scorer.v1",
+            "spans_key": DEFAULT_SPANS_KEY,
+        },
+    },
+    default_score_weights={
+        f"spans_{DEFAULT_SPANS_KEY}_f": 1.0,
+        f"spans_{DEFAULT_SPANS_KEY}_p": 0.0,
+        f"spans_{DEFAULT_SPANS_KEY}_r": 0.0,
+        f"spans_{DEFAULT_SPANS_KEY}_per_type": None,
+    },
+)
+def make_span_ruler(
+    nlp: Language,
+    name: str,
+    spans_key: Optional[str],
+    spans_filter: Optional[Callable[[Iterable[Span], Iterable[Span]], Iterable[Span]]],
+    annotate_ents: bool,
+    ents_filter: Callable[[Iterable[Span], Iterable[Span]], Iterable[Span]],
+    phrase_matcher_attr: Optional[Union[int, str]],
+    validate: bool,
+    overwrite: bool,
+    scorer: Optional[Callable],
+):
+    return SpanRuler(
+        nlp,
+        name,
+        spans_key=spans_key,
+        spans_filter=spans_filter,
+        annotate_ents=annotate_ents,
+        ents_filter=ents_filter,
+        phrase_matcher_attr=phrase_matcher_attr,
+        validate=validate,
+        overwrite=overwrite,
+        scorer=scorer,
+    )
+
+
+def prioritize_new_ents_filter(
+    entities: Iterable[Span], spans: Iterable[Span]
+) -> List[Span]:
+    """Merge entities and spans into one list without overlaps by allowing
+    spans to overwrite any entities that they overlap with. Intended to
+    replicate the overwrite_ents=True behavior from the EntityRuler.
+
+    entities (Iterable[Span]): The entities, already filtered for overlaps.
+    spans (Iterable[Span]): The spans to merge, may contain overlaps.
+    RETURNS (List[Span]): Filtered list of non-overlapping spans.
+    """
+    get_sort_key = lambda span: (span.end - span.start, -span.start)
+    spans = sorted(spans, key=get_sort_key, reverse=True)
+    entities = list(entities)
+    new_entities = []
+    seen_tokens: Set[int] = set()
+    for span in spans:
+        start = span.start
+        end = span.end
+        if all(token.i not in seen_tokens for token in span):
+            new_entities.append(span)
+            entities = [e for e in entities if not (e.start < end and e.end > start)]
+            seen_tokens.update(range(start, end))
+    return entities + new_entities
+
+
+@registry.misc("spacy.prioritize_new_ents_filter.v1")
+def make_prioritize_new_ents_filter():
+    return prioritize_new_ents_filter
+
+
+def prioritize_existing_ents_filter(
+    entities: Iterable[Span], spans: Iterable[Span]
+) -> List[Span]:
+    """Merge entities and spans into one list without overlaps by prioritizing
+    existing entities. Intended to replicate the overwrite_ents=False behavior
+    from the EntityRuler.
+
+    entities (Iterable[Span]): The entities, already filtered for overlaps.
+    spans (Iterable[Span]): The spans to merge, may contain overlaps.
+    RETURNS (List[Span]): Filtered list of non-overlapping spans.
+    """
+    get_sort_key = lambda span: (span.end - span.start, -span.start)
+    spans = sorted(spans, key=get_sort_key, reverse=True)
+    entities = list(entities)
+    new_entities = []
+    seen_tokens: Set[int] = set()
+    seen_tokens.update(*(range(ent.start, ent.end) for ent in entities))
+    for span in spans:
+        start = span.start
+        end = span.end
+        if all(token.i not in seen_tokens for token in span):
+            new_entities.append(span)
+            seen_tokens.update(range(start, end))
+    return entities + new_entities
+
+
+@registry.misc("spacy.prioritize_existing_ents_filter.v1")
+def make_preverse_existing_ents_filter():
+    return prioritize_existing_ents_filter
+
+
+def overlapping_labeled_spans_score(
+    examples: Iterable[Example], *, spans_key=DEFAULT_SPANS_KEY, **kwargs
+) -> Dict[str, Any]:
+    kwargs = dict(kwargs)
+    attr_prefix = f"spans_"
+    kwargs.setdefault("attr", f"{attr_prefix}{spans_key}")
+    kwargs.setdefault("allow_overlap", True)
+    kwargs.setdefault("labeled", True)
+    kwargs.setdefault(
+        "getter", lambda doc, key: doc.spans.get(key[len(attr_prefix) :], [])
+    )
+    kwargs.setdefault("has_annotation", lambda doc: spans_key in doc.spans)
+    return Scorer.score_spans(examples, **kwargs)
+
+
+@registry.scorers("spacy.overlapping_labeled_spans_scorer.v1")
+def make_overlapping_labeled_spans_scorer(spans_key: str = DEFAULT_SPANS_KEY):
+    return partial(overlapping_labeled_spans_score, spans_key=spans_key)
+
+
+class SpanRuler(Pipe):
+    """The SpanRuler lets you add spans to the `Doc.spans` using token-based
+    rules or exact phrase matches.
+
+    DOCS: https://spacy.io/api/spanruler
+    USAGE: https://spacy.io/usage/rule-based-matching#spanruler
+    """
+
+    def __init__(
+        self,
+        nlp: Language,
+        name: str = "span_ruler",
+        *,
+        spans_key: Optional[str] = DEFAULT_SPANS_KEY,
+        spans_filter: Optional[
+            Callable[[Iterable[Span], Iterable[Span]], Iterable[Span]]
+        ] = None,
+        annotate_ents: bool = False,
+        ents_filter: Callable[
+            [Iterable[Span], Iterable[Span]], Iterable[Span]
+        ] = util.filter_chain_spans,
+        phrase_matcher_attr: Optional[Union[int, str]] = None,
+        validate: bool = False,
+        overwrite: bool = False,
+        scorer: Optional[Callable] = partial(
+            overlapping_labeled_spans_score, spans_key=DEFAULT_SPANS_KEY
+        ),
+    ) -> None:
+        """Initialize the span ruler. If patterns are supplied here, they
+        need to be a list of dictionaries with a `"label"` and `"pattern"`
+        key. A pattern can either be a token pattern (list) or a phrase pattern
+        (string). For example: `{'label': 'ORG', 'pattern': 'Apple'}`.
+
+        nlp (Language): The shared nlp object to pass the vocab to the matchers
+            and process phrase patterns.
+        name (str): Instance name of the current pipeline component. Typically
+            passed in automatically from the factory when the component is
+            added. Used to disable the current span ruler while creating
+            phrase patterns with the nlp object.
+        spans_key (Optional[str]): The spans key to save the spans under. If
+            `None`, no spans are saved. Defaults to "ruler".
+        spans_filter (Optional[Callable[[Iterable[Span], Iterable[Span]], List[Span]]):
+            The optional method to filter spans before they are assigned to
+            doc.spans. Defaults to `None`.
+        annotate_ents (bool): Whether to save spans to doc.ents. Defaults to
+            `False`.
+        ents_filter (Callable[[Iterable[Span], Iterable[Span]], List[Span]]):
+            The method to filter spans before they are assigned to doc.ents.
+            Defaults to `util.filter_chain_spans`.
+        phrase_matcher_attr (Optional[Union[int, str]]): Token attribute to
+            match on, passed to the internal PhraseMatcher as `attr`. Defaults
+            to `None`.
+        validate (bool): Whether patterns should be validated, passed to
+            Matcher and PhraseMatcher as `validate`.
+        overwrite (bool): Whether to remove any existing spans under this spans
+            key if `spans_key` is set, and/or to remove any ents under `doc.ents` if
+            `annotate_ents` is set. Defaults to `True`.
+        scorer (Optional[Callable]): The scoring method. Defaults to
+            spacy.pipeline.span_ruler.overlapping_labeled_spans_score.
+
+        DOCS: https://spacy.io/api/spanruler#init
+        """
+        self.nlp = nlp
+        self.name = name
+        self.spans_key = spans_key
+        self.annotate_ents = annotate_ents
+        self.phrase_matcher_attr = phrase_matcher_attr
+        self.validate = validate
+        self.overwrite = overwrite
+        self.spans_filter = spans_filter
+        self.ents_filter = ents_filter
+        self.scorer = scorer
+        self._match_label_id_map: Dict[int, Dict[str, str]] = {}
+        self.clear()
+
+    def __len__(self) -> int:
+        """The number of all labels added to the span ruler."""
+        return len(self._patterns)
+
+    def __contains__(self, label: str) -> bool:
+        """Whether a label is present in the patterns."""
+        for label_id in self._match_label_id_map.values():
+            if label_id["label"] == label:
+                return True
+        return False
+
+    @property
+    def key(self) -> Optional[str]:
+        """Key of the doc.spans dict to save the spans under."""
+        return self.spans_key
+
+    def __call__(self, doc: Doc) -> Doc:
+        """Find matches in document and add them as entities.
+
+        doc (Doc): The Doc object in the pipeline.
+        RETURNS (Doc): The Doc with added entities, if available.
+
+        DOCS: https://spacy.io/api/spanruler#call
+        """
+        error_handler = self.get_error_handler()
+        try:
+            matches = self.match(doc)
+            self.set_annotations(doc, matches)
+            return doc
+        except Exception as e:
+            return error_handler(self.name, self, [doc], e)
+
+    def match(self, doc: Doc):
+        self._require_patterns()
+        with warnings.catch_warnings():
+            warnings.filterwarnings("ignore", message="\\[W036")
+            matches = cast(
+                List[Tuple[int, int, int]],
+                list(self.matcher(doc)) + list(self.phrase_matcher(doc)),
+            )
+        deduplicated_matches = set(
+            Span(
+                doc,
+                start,
+                end,
+                label=self._match_label_id_map[m_id]["label"],
+                span_id=self._match_label_id_map[m_id]["id"],
+            )
+            for m_id, start, end in matches
+            if start != end
+        )
+        return sorted(list(deduplicated_matches))
+
+    def set_annotations(self, doc, matches):
+        """Modify the document in place"""
+        # set doc.spans if spans_key is set
+        if self.key:
+            spans = []
+            if self.key in doc.spans and not self.overwrite:
+                spans = doc.spans[self.key]
+            spans.extend(
+                self.spans_filter(spans, matches) if self.spans_filter else matches
+            )
+            doc.spans[self.key] = spans
+        # set doc.ents if annotate_ents is set
+        if self.annotate_ents:
+            spans = []
+            if not self.overwrite:
+                spans = list(doc.ents)
+            spans = self.ents_filter(spans, matches)
+            try:
+                doc.ents = sorted(spans)
+            except ValueError:
+                raise ValueError(Errors.E854)
+
+    @property
+    def labels(self) -> Tuple[str, ...]:
+        """All labels present in the match patterns.
+
+        RETURNS (set): The string labels.
+
+        DOCS: https://spacy.io/api/spanruler#labels
+        """
+        return tuple(sorted(set([cast(str, p["label"]) for p in self._patterns])))
+
+    @property
+    def ids(self) -> Tuple[str, ...]:
+        """All IDs present in the match patterns.
+
+        RETURNS (set): The string IDs.
+
+        DOCS: https://spacy.io/api/spanruler#ids
+        """
+        return tuple(
+            sorted(set([cast(str, p.get("id")) for p in self._patterns]) - set([None]))
+        )
+
+    def initialize(
+        self,
+        get_examples: Callable[[], Iterable[Example]],
+        *,
+        nlp: Optional[Language] = None,
+        patterns: Optional[Sequence[PatternType]] = None,
+    ):
+        """Initialize the pipe for training.
+
+        get_examples (Callable[[], Iterable[Example]]): Function that
+            returns a representative sample of gold-standard Example objects.
+        nlp (Language): The current nlp object the component is part of.
+        patterns (Optional[Iterable[PatternType]]): The list of patterns.
+
+        DOCS: https://spacy.io/api/spanruler#initialize
+        """
+        self.clear()
+        if patterns:
+            self.add_patterns(patterns)  # type: ignore[arg-type]
+
+    @property
+    def patterns(self) -> List[PatternType]:
+        """Get all patterns that were added to the span ruler.
+
+        RETURNS (list): The original patterns, one dictionary per pattern.
+
+        DOCS: https://spacy.io/api/spanruler#patterns
+        """
+        return self._patterns
+
+    def add_patterns(self, patterns: List[PatternType]) -> None:
+        """Add patterns to the span ruler. A pattern can either be a token
+        pattern (list of dicts) or a phrase pattern (string). For example:
+        {'label': 'ORG', 'pattern': 'Apple'}
+        {'label': 'ORG', 'pattern': 'Apple', 'id': 'apple'}
+        {'label': 'GPE', 'pattern': [{'lower': 'san'}, {'lower': 'francisco'}]}
+
+        patterns (list): The patterns to add.
+
+        DOCS: https://spacy.io/api/spanruler#add_patterns
+        """
+
+        # disable the nlp components after this one in case they haven't been
+        # initialized / deserialized yet
+        try:
+            current_index = -1
+            for i, (name, pipe) in enumerate(self.nlp.pipeline):
+                if self == pipe:
+                    current_index = i
+                    break
+            subsequent_pipes = [pipe for pipe in self.nlp.pipe_names[current_index:]]
+        except ValueError:
+            subsequent_pipes = []
+        with self.nlp.select_pipes(disable=subsequent_pipes):
+            phrase_pattern_labels = []
+            phrase_pattern_texts = []
+            for entry in patterns:
+                p_label = cast(str, entry["label"])
+                p_id = cast(str, entry.get("id", ""))
+                label = repr((p_label, p_id))
+                self._match_label_id_map[self.nlp.vocab.strings.as_int(label)] = {
+                    "label": p_label,
+                    "id": p_id,
+                }
+                if isinstance(entry["pattern"], str):
+                    phrase_pattern_labels.append(label)
+                    phrase_pattern_texts.append(entry["pattern"])
+                elif isinstance(entry["pattern"], list):
+                    self.matcher.add(label, [entry["pattern"]])
+                else:
+                    raise ValueError(Errors.E097.format(pattern=entry["pattern"]))
+                self._patterns.append(entry)
+            for label, pattern in zip(
+                phrase_pattern_labels,
+                self.nlp.pipe(phrase_pattern_texts),
+            ):
+                self.phrase_matcher.add(label, [pattern])
+
+    def clear(self) -> None:
+        """Reset all patterns.
+
+        RETURNS: None
+        DOCS: https://spacy.io/api/spanruler#clear
+        """
+        self._patterns: List[PatternType] = []
+        self.matcher: Matcher = Matcher(self.nlp.vocab, validate=self.validate)
+        self.phrase_matcher: PhraseMatcher = PhraseMatcher(
+            self.nlp.vocab,
+            attr=self.phrase_matcher_attr,
+            validate=self.validate,
+        )
+
+    def remove(self, label: str) -> None:
+        """Remove a pattern by its label.
+
+        label (str): Label of the pattern to be removed.
+        RETURNS: None
+        DOCS: https://spacy.io/api/spanruler#remove
+        """
+        if label not in self:
+            raise ValueError(
+                Errors.E1024.format(attr_type="label", label=label, component=self.name)
+            )
+        self._patterns = [p for p in self._patterns if p["label"] != label]
+        for m_label in self._match_label_id_map:
+            if self._match_label_id_map[m_label]["label"] == label:
+                m_label_str = self.nlp.vocab.strings.as_string(m_label)
+                if m_label_str in self.phrase_matcher:
+                    self.phrase_matcher.remove(m_label_str)
+                if m_label_str in self.matcher:
+                    self.matcher.remove(m_label_str)
+
+    def remove_by_id(self, pattern_id: str) -> None:
+        """Remove a pattern by its pattern ID.
+
+        pattern_id (str): ID of the pattern to be removed.
+        RETURNS: None
+        DOCS: https://spacy.io/api/spanruler#remove_by_id
+        """
+        orig_len = len(self)
+        self._patterns = [p for p in self._patterns if p.get("id") != pattern_id]
+        if orig_len == len(self):
+            raise ValueError(
+                Errors.E1024.format(
+                    attr_type="ID", label=pattern_id, component=self.name
+                )
+            )
+        for m_label in self._match_label_id_map:
+            if self._match_label_id_map[m_label]["id"] == pattern_id:
+                m_label_str = self.nlp.vocab.strings.as_string(m_label)
+                if m_label_str in self.phrase_matcher:
+                    self.phrase_matcher.remove(m_label_str)
+                if m_label_str in self.matcher:
+                    self.matcher.remove(m_label_str)
+
+    def _require_patterns(self) -> None:
+        """Raise a warning if this component has no patterns defined."""
+        if len(self) == 0:
+            warnings.warn(Warnings.W036.format(name=self.name))
+
+    def from_bytes(
+        self, bytes_data: bytes, *, exclude: Iterable[str] = SimpleFrozenList()
+    ) -> "SpanRuler":
+        """Load the span ruler from a bytestring.
+
+        bytes_data (bytes): The bytestring to load.
+        RETURNS (SpanRuler): The loaded span ruler.
+
+        DOCS: https://spacy.io/api/spanruler#from_bytes
+        """
+        self.clear()
+        deserializers = {
+            "patterns": lambda b: self.add_patterns(srsly.json_loads(b)),
+        }
+        util.from_bytes(bytes_data, deserializers, exclude)
+        return self
+
+    def to_bytes(self, *, exclude: Iterable[str] = SimpleFrozenList()) -> bytes:
+        """Serialize the span ruler to a bytestring.
+
+        RETURNS (bytes): The serialized patterns.
+
+        DOCS: https://spacy.io/api/spanruler#to_bytes
+        """
+        serializers = {
+            "patterns": lambda: srsly.json_dumps(self.patterns),
+        }
+        return util.to_bytes(serializers, exclude)
+
+    def from_disk(
+        self, path: Union[str, Path], *, exclude: Iterable[str] = SimpleFrozenList()
+    ) -> "SpanRuler":
+        """Load the span ruler from a directory.
+
+        path (Union[str, Path]): A path to a directory.
+        RETURNS (SpanRuler): The loaded span ruler.
+
+        DOCS: https://spacy.io/api/spanruler#from_disk
+        """
+        self.clear()
+        path = ensure_path(path)
+        deserializers = {
+            "patterns": lambda p: self.add_patterns(srsly.read_jsonl(p)),
+        }
+        util.from_disk(path, deserializers, {})
+        return self
+
+    def to_disk(
+        self, path: Union[str, Path], *, exclude: Iterable[str] = SimpleFrozenList()
+    ) -> None:
+        """Save the span ruler patterns to a directory.
+
+        path (Union[str, Path]): A path to a directory.
+
+        DOCS: https://spacy.io/api/spanruler#to_disk
+        """
+        path = ensure_path(path)
+        serializers = {
+            "patterns": lambda p: srsly.write_jsonl(p, self.patterns),
+        }
+        util.to_disk(path, serializers, {})

spacy/pipeline/spancat.py

@@ -75,7 +75,7 @@ def build_ngram_suggester(sizes: List[int]) -> Suggester:
                 if spans:
                     assert spans[-1].ndim == 2, spans[-1].shape
             lengths.append(length)
-        lengths_array = cast(Ints1d, ops.asarray(lengths, dtype="i"))
+        lengths_array = ops.asarray1i(lengths)
         if len(spans) > 0:
             output = Ragged(ops.xp.vstack(spans), lengths_array)
         else:

spacy/pipeline/textcat.py

@@ -192,7 +192,7 @@ class TextCategorizer(TrainablePipe):
         if not any(len(doc) for doc in docs):
             # Handle cases where there are no tokens in any docs.
             tensors = [doc.tensor for doc in docs]
-            xp = get_array_module(tensors)
+            xp = self.model.ops.xp
             scores = xp.zeros((len(list(docs)), len(self.labels)))
             return scores
         scores = self.model.predict(docs)

spacy/pipeline/transition_parser.pxd

@@ -1,4 +1,5 @@
 from cymem.cymem cimport Pool
+from thinc.backends.cblas cimport CBlas
 
 from ..vocab cimport Vocab
 from .trainable_pipe cimport TrainablePipe
@@ -12,7 +13,7 @@ cdef class Parser(TrainablePipe):
     cdef readonly TransitionSystem moves
     cdef public object _multitasks
 
-    cdef void _parseC(self, StateC** states,
+    cdef void _parseC(self, CBlas cblas, StateC** states,
             WeightsC weights, SizesC sizes) nogil
 
     cdef void c_transition_batch(self, StateC** states, const float* scores,

spacy/pipeline/transition_parser.pyx

@@ -9,7 +9,7 @@ from libc.stdlib cimport calloc, free
 import random
 
 import srsly
-from thinc.api import set_dropout_rate, CupyOps
+from thinc.api import get_ops, set_dropout_rate, CupyOps, NumpyOps
 from thinc.extra.search cimport Beam
 import numpy.random
 import numpy
@@ -30,6 +30,9 @@ from ..errors import Errors, Warnings
 from .. import util
 
 
+NUMPY_OPS = NumpyOps()
+
+
 cdef class Parser(TrainablePipe):
     """
     Base class of the DependencyParser and EntityRecognizer.
@@ -259,6 +262,12 @@ cdef class Parser(TrainablePipe):
     def greedy_parse(self, docs, drop=0.):
         cdef vector[StateC*] states
         cdef StateClass state
+        ops = self.model.ops
+        cdef CBlas cblas
+        if isinstance(ops, CupyOps):
+            cblas = NUMPY_OPS.cblas()
+        else:
+            cblas = ops.cblas()
         self._ensure_labels_are_added(docs)
         set_dropout_rate(self.model, drop)
         batch = self.moves.init_batch(docs)
@@ -269,8 +278,7 @@ cdef class Parser(TrainablePipe):
                 states.push_back(state.c)
         sizes = get_c_sizes(model, states.size())
         with nogil:
-            self._parseC(&states[0],
+            self._parseC(cblas, &states[0], weights, sizes)
-                weights, sizes)
         model.clear_memory()
         del model
         return batch
@@ -297,14 +305,13 @@ cdef class Parser(TrainablePipe):
         del model
         return list(batch)
 
-    cdef void _parseC(self, StateC** states,
+    cdef void _parseC(self, CBlas cblas, StateC** states,
             WeightsC weights, SizesC sizes) nogil:
         cdef int i, j
         cdef vector[StateC*] unfinished
         cdef ActivationsC activations = alloc_activations(sizes)
         while sizes.states >= 1:
-            predict_states(&activations,
+            predict_states(cblas, &activations, states, &weights, sizes)
-                states, &weights, sizes)
             # Validate actions, argmax, take action.
             self.c_transition_batch(states,
                 activations.scores, sizes.classes, sizes.states)

spacy/schemas.py

@@ -3,12 +3,13 @@ from typing import Iterable, TypeVar, TYPE_CHECKING
 from .compat import Literal
 from enum import Enum
 from pydantic import BaseModel, Field, ValidationError, validator, create_model
-from pydantic import StrictStr, StrictInt, StrictFloat, StrictBool
+from pydantic import StrictStr, StrictInt, StrictFloat, StrictBool, ConstrainedStr
 from pydantic.main import ModelMetaclass
 from thinc.api import Optimizer, ConfigValidationError, Model
 from thinc.config import Promise
 from collections import defaultdict
 import inspect
+import re
 
 from .attrs import NAMES
 from .lookups import Lookups
@@ -104,7 +105,7 @@ def get_arg_model(
         sig_args[param.name] = (annotation, default)
     is_strict = strict and not has_variable
     sig_args["__config__"] = ArgSchemaConfig if is_strict else ArgSchemaConfigExtra  # type: ignore[assignment]
-    return create_model(name, **sig_args)  # type: ignore[arg-type, return-value]
+    return create_model(name, **sig_args)  # type: ignore[call-overload, arg-type, return-value]
 
 
 def validate_init_settings(
@@ -198,13 +199,18 @@ class TokenPatternNumber(BaseModel):
         return v
 
 
-class TokenPatternOperator(str, Enum):
+class TokenPatternOperatorSimple(str, Enum):
     plus: StrictStr = StrictStr("+")
-    start: StrictStr = StrictStr("*")
+    star: StrictStr = StrictStr("*")
     question: StrictStr = StrictStr("?")
     exclamation: StrictStr = StrictStr("!")
 
 
+class TokenPatternOperatorMinMax(ConstrainedStr):
+    regex = re.compile("^({\d+}|{\d+,\d*}|{\d*,\d+})$")
+
+
+TokenPatternOperator = Union[TokenPatternOperatorSimple, TokenPatternOperatorMinMax]
 StringValue = Union[TokenPatternString, StrictStr]
 NumberValue = Union[TokenPatternNumber, StrictInt, StrictFloat]
 UnderscoreValue = Union[
@@ -485,3 +491,29 @@ class RecommendationSchema(BaseModel):
     word_vectors: Optional[str] = None
     transformer: Optional[RecommendationTrf] = None
     has_letters: bool = True
+
+
+class DocJSONSchema(BaseModel):
+    """
+    JSON/dict format for JSON representation of Doc objects.
+    """
+
+    cats: Optional[Dict[StrictStr, StrictFloat]] = Field(
+        None, title="Categories with corresponding probabilities"
+    )
+    ents: Optional[List[Dict[StrictStr, Union[StrictInt, StrictStr]]]] = Field(
+        None, title="Information on entities"
+    )
+    sents: Optional[List[Dict[StrictStr, StrictInt]]] = Field(
+        None, title="Indices of sentences' start and end indices"
+    )
+    text: StrictStr = Field(..., title="Document text")
+    spans: Dict[StrictStr, List[Dict[StrictStr, Union[StrictStr, StrictInt]]]] = Field(
+        None, title="Span information - end/start indices, label, KB ID"
+    )
+    tokens: List[Dict[StrictStr, Union[StrictStr, StrictInt]]] = Field(
+        ..., title="Token information - ID, start, annotations"
+    )
+    _: Optional[Dict[StrictStr, Any]] = Field(
+        None, title="Any custom data stored in the document's _ attribute"
+    )

spacy/strings.pxd

@@ -26,4 +26,4 @@ cdef class StringStore:
     cdef public PreshMap _map
 
     cdef const Utf8Str* intern_unicode(self, str py_string)
-    cdef const Utf8Str* _intern_utf8(self, char* utf8_string, int length)
+    cdef const Utf8Str* _intern_utf8(self, char* utf8_string, int length, hash_t* precalculated_hash)

spacy/strings.pyx

@@ -14,6 +14,13 @@ from .symbols import NAMES as SYMBOLS_BY_INT
 from .errors import Errors
 from . import util
 
+# Not particularly elegant, but this is faster than `isinstance(key, numbers.Integral)`
+cdef inline bint _try_coerce_to_hash(object key, hash_t* out_hash):
+    try:
+        out_hash[0] = key
+        return True
+    except:
+        return False
 
 def get_string_id(key):
     """Get a string ID, handling the reserved symbols correctly. If the key is
@@ -22,15 +29,27 @@ def get_string_id(key):
     This function optimises for convenience over performance, so shouldn't be
     used in tight loops.
     """
-    if not isinstance(key, str):
+    cdef hash_t str_hash    
-        return key
+    if isinstance(key, str):
-    elif key in SYMBOLS_BY_STR:
+        if len(key) == 0:
-        return SYMBOLS_BY_STR[key]
-    elif not key:
             return 0
+
+        symbol = SYMBOLS_BY_STR.get(key, None)
+        if symbol is not None:
+            return symbol
         else:
             chars = key.encode("utf8")
             return hash_utf8(chars, len(chars))
+    elif _try_coerce_to_hash(key, &str_hash):
+        # Coerce the integral key to the expected primitive hash type.
+        # This ensures that custom/overloaded "primitive" data types
+        # such as those implemented by numpy are not inadvertently used 
+        # downsteam (as these are internally implemented as custom PyObjects 
+        # whose comparison operators can incur a significant overhead).
+        return str_hash
+    else:
+        # TODO: Raise an error instead
+        return key
 
 
 cpdef hash_t hash_string(str string) except 0:
@@ -110,24 +129,32 @@ cdef class StringStore:
         string_or_id (bytes, str or uint64): The value to encode.
         Returns (str / uint64): The value to be retrieved.
         """
-        if isinstance(string_or_id, str) and len(string_or_id) == 0:
+        cdef hash_t str_hash
-            return 0
+        cdef Utf8Str* utf8str = NULL
-        elif string_or_id == 0:
+
-            return ""
-        elif string_or_id in SYMBOLS_BY_STR:
-            return SYMBOLS_BY_STR[string_or_id]
-        cdef hash_t key
         if isinstance(string_or_id, str):
-            key = hash_string(string_or_id)
+            if len(string_or_id) == 0:
-            return key
+                return 0
-        elif isinstance(string_or_id, bytes):
+
-            key = hash_utf8(string_or_id, len(string_or_id))
+            # Return early if the string is found in the symbols LUT.
-            return key
+            symbol = SYMBOLS_BY_STR.get(string_or_id, None)
-        elif string_or_id < len(SYMBOLS_BY_INT):
+            if symbol is not None:
-            return SYMBOLS_BY_INT[string_or_id]
+                return symbol
             else:
-            key = string_or_id
+                return hash_string(string_or_id)
-            utf8str = <Utf8Str*>self._map.get(key)
+        elif isinstance(string_or_id, bytes):
+            return hash_utf8(string_or_id, len(string_or_id))
+        elif _try_coerce_to_hash(string_or_id, &str_hash):
+            if str_hash == 0:
+                return ""
+            elif str_hash < len(SYMBOLS_BY_INT):
+                return SYMBOLS_BY_INT[str_hash]
+            else:
+                utf8str = <Utf8Str*>self._map.get(str_hash)
+        else:
+            # TODO: Raise an error instead
+            utf8str = <Utf8Str*>self._map.get(string_or_id)
+
         if utf8str is NULL:
             raise KeyError(Errors.E018.format(hash_value=string_or_id))
         else:
@@ -153,19 +180,22 @@ cdef class StringStore:
         string (str): The string to add.
         RETURNS (uint64): The string's hash value.
         """
+        cdef hash_t str_hash
         if isinstance(string, str):
             if string in SYMBOLS_BY_STR:
                 return SYMBOLS_BY_STR[string]
-            key = hash_string(string)
+
-            self.intern_unicode(string)
+            string = string.encode("utf8")
+            str_hash = hash_utf8(string, len(string))
+            self._intern_utf8(string, len(string), &str_hash)
         elif isinstance(string, bytes):
             if string in SYMBOLS_BY_STR:
                 return SYMBOLS_BY_STR[string]
-            key = hash_utf8(string, len(string))
+            str_hash = hash_utf8(string, len(string))
-            self._intern_utf8(string, len(string))
+            self._intern_utf8(string, len(string), &str_hash)
         else:
             raise TypeError(Errors.E017.format(value_type=type(string)))
-        return key
+        return str_hash
 
     def __len__(self):
         """The number of strings in the store.
@@ -174,30 +204,29 @@ cdef class StringStore:
         """
         return self.keys.size()
 
-    def __contains__(self, string not None):
+    def __contains__(self, string_or_id not None):
-        """Check whether a string is in the store.
+        """Check whether a string or ID is in the store.
 
-        string (str): The string to check.
+        string_or_id (str or int): The string to check.
         RETURNS (bool): Whether the store contains the string.
         """
-        cdef hash_t key
+        cdef hash_t str_hash
-        if isinstance(string, int) or isinstance(string, long):
+        if isinstance(string_or_id, str):
-            if string == 0:
+            if len(string_or_id) == 0:
                 return True
-            key = string
+            elif string_or_id in SYMBOLS_BY_STR:
-        elif len(string) == 0:
                 return True
-        elif string in SYMBOLS_BY_STR:
+            str_hash = hash_string(string_or_id)
-            return True
+        elif _try_coerce_to_hash(string_or_id, &str_hash):
-        elif isinstance(string, str):
+            pass
-            key = hash_string(string)
         else:
-            string = string.encode("utf8")
+            # TODO: Raise an error instead
-            key = hash_utf8(string, len(string))
+            return self._map.get(string_or_id) is not NULL
-        if key < len(SYMBOLS_BY_INT):
+
+        if str_hash < len(SYMBOLS_BY_INT):
             return True
         else:
-            return self._map.get(key) is not NULL
+            return self._map.get(str_hash) is not NULL
 
     def __iter__(self):
         """Iterate over the strings in the store, in order.
@@ -272,13 +301,13 @@ cdef class StringStore:
     cdef const Utf8Str* intern_unicode(self, str py_string):
         # 0 means missing, but we don't bother offsetting the index.
         cdef bytes byte_string = py_string.encode("utf8")
-        return self._intern_utf8(byte_string, len(byte_string))
+        return self._intern_utf8(byte_string, len(byte_string), NULL)
 
     @cython.final
-    cdef const Utf8Str* _intern_utf8(self, char* utf8_string, int length):
+    cdef const Utf8Str* _intern_utf8(self, char* utf8_string, int length, hash_t* precalculated_hash):
         # TODO: This function's API/behaviour is an unholy mess...
         # 0 means missing, but we don't bother offsetting the index.
-        cdef hash_t key = hash_utf8(utf8_string, length)
+        cdef hash_t key = precalculated_hash[0] if precalculated_hash is not NULL else hash_utf8(utf8_string, length)
         cdef Utf8Str* value = <Utf8Str*>self._map.get(key)
         if value is not NULL:
             return value

spacy/tests/conftest.py

@@ -1,5 +1,11 @@
 import pytest
 from spacy.util import get_lang_class
+from hypothesis import settings
+
+# Functionally disable deadline settings for tests
+# to prevent spurious test failures in CI builds.
+settings.register_profile("no_deadlines", deadline=2 * 60 * 1000)  # in ms
+settings.load_profile("no_deadlines")
 
 
 def pytest_addoption(parser):

spacy/tests/doc/test_doc_api.py

@@ -11,7 +11,7 @@ from spacy.lang.en import English
 from spacy.lang.xx import MultiLanguage
 from spacy.language import Language
 from spacy.lexeme import Lexeme
-from spacy.tokens import Doc, Span, Token
+from spacy.tokens import Doc, Span, SpanGroup, Token
 from spacy.vocab import Vocab
 
 from .test_underscore import clean_underscore  # noqa: F401
@@ -964,3 +964,13 @@ def test_doc_spans_copy(en_tokenizer):
     assert weakref.ref(doc1) == doc1.spans.doc_ref
     doc2 = doc1.copy()
     assert weakref.ref(doc2) == doc2.spans.doc_ref
+
+
+def test_doc_spans_setdefault(en_tokenizer):
+    doc = en_tokenizer("Some text about Colombia and the Czech Republic")
+    doc.spans.setdefault("key1")
+    assert len(doc.spans["key1"]) == 0
+    doc.spans.setdefault("key2", default=[doc[0:1]])
+    assert len(doc.spans["key2"]) == 1
+    doc.spans.setdefault("key3", default=SpanGroup(doc, spans=[doc[0:1], doc[1:2]]))
+    assert len(doc.spans["key3"]) == 2

spacy/tests/doc/test_json_doc_conversion.py

@@ -0,0 +1,191 @@
+import pytest
+import spacy
+from spacy import schemas
+from spacy.tokens import Doc, Span
+
+
+@pytest.fixture()
+def doc(en_vocab):
+    words = ["c", "d", "e"]
+    pos = ["VERB", "NOUN", "NOUN"]
+    tags = ["VBP", "NN", "NN"]
+    heads = [0, 0, 1]
+    deps = ["ROOT", "dobj", "dobj"]
+    ents = ["O", "B-ORG", "O"]
+    morphs = ["Feat1=A", "Feat1=B", "Feat1=A|Feat2=D"]
+
+    return Doc(
+        en_vocab,
+        words=words,
+        pos=pos,
+        tags=tags,
+        heads=heads,
+        deps=deps,
+        ents=ents,
+        morphs=morphs,
+    )
+
+
+@pytest.fixture()
+def doc_without_deps(en_vocab):
+    words = ["c", "d", "e"]
+    pos = ["VERB", "NOUN", "NOUN"]
+    tags = ["VBP", "NN", "NN"]
+    ents = ["O", "B-ORG", "O"]
+    morphs = ["Feat1=A", "Feat1=B", "Feat1=A|Feat2=D"]
+
+    return Doc(
+        en_vocab,
+        words=words,
+        pos=pos,
+        tags=tags,
+        ents=ents,
+        morphs=morphs,
+        sent_starts=[True, False, True],
+    )
+
+
+def test_doc_to_json(doc):
+    json_doc = doc.to_json()
+    assert json_doc["text"] == "c d e "
+    assert len(json_doc["tokens"]) == 3
+    assert json_doc["tokens"][0]["pos"] == "VERB"
+    assert json_doc["tokens"][0]["tag"] == "VBP"
+    assert json_doc["tokens"][0]["dep"] == "ROOT"
+    assert len(json_doc["ents"]) == 1
+    assert json_doc["ents"][0]["start"] == 2  # character offset!
+    assert json_doc["ents"][0]["end"] == 3  # character offset!
+    assert json_doc["ents"][0]["label"] == "ORG"
+    assert not schemas.validate(schemas.DocJSONSchema, json_doc)
+
+
+def test_doc_to_json_underscore(doc):
+    Doc.set_extension("json_test1", default=False)
+    Doc.set_extension("json_test2", default=False)
+    doc._.json_test1 = "hello world"
+    doc._.json_test2 = [1, 2, 3]
+    json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
+    assert "_" in json_doc
+    assert json_doc["_"]["json_test1"] == "hello world"
+    assert json_doc["_"]["json_test2"] == [1, 2, 3]
+    assert not schemas.validate(schemas.DocJSONSchema, json_doc)
+
+
+def test_doc_to_json_underscore_error_attr(doc):
+    """Test that Doc.to_json() raises an error if a custom attribute doesn't
+    exist in the ._ space."""
+    with pytest.raises(ValueError):
+        doc.to_json(underscore=["json_test3"])
+
+
+def test_doc_to_json_underscore_error_serialize(doc):
+    """Test that Doc.to_json() raises an error if a custom attribute value
+    isn't JSON-serializable."""
+    Doc.set_extension("json_test4", method=lambda doc: doc.text)
+    with pytest.raises(ValueError):
+        doc.to_json(underscore=["json_test4"])
+
+
+def test_doc_to_json_span(doc):
+    """Test that Doc.to_json() includes spans"""
+    doc.spans["test"] = [Span(doc, 0, 2, "test"), Span(doc, 0, 1, "test")]
+    json_doc = doc.to_json()
+    assert "spans" in json_doc
+    assert len(json_doc["spans"]) == 1
+    assert len(json_doc["spans"]["test"]) == 2
+    assert json_doc["spans"]["test"][0]["start"] == 0
+    assert not schemas.validate(schemas.DocJSONSchema, json_doc)
+
+
+def test_json_to_doc(doc):
+    new_doc = Doc(doc.vocab).from_json(doc.to_json(), validate=True)
+    new_tokens = [token for token in new_doc]
+    assert new_doc.text == doc.text == "c d e "
+    assert len(new_tokens) == len([token for token in doc]) == 3
+    assert new_tokens[0].pos == doc[0].pos
+    assert new_tokens[0].tag == doc[0].tag
+    assert new_tokens[0].dep == doc[0].dep
+    assert new_tokens[0].head.idx == doc[0].head.idx
+    assert new_tokens[0].lemma == doc[0].lemma
+    assert len(new_doc.ents) == 1
+    assert new_doc.ents[0].start == 1
+    assert new_doc.ents[0].end == 2
+    assert new_doc.ents[0].label_ == "ORG"
+
+
+def test_json_to_doc_underscore(doc):
+    if not Doc.has_extension("json_test1"):
+        Doc.set_extension("json_test1", default=False)
+    if not Doc.has_extension("json_test2"):
+        Doc.set_extension("json_test2", default=False)
+
+    doc._.json_test1 = "hello world"
+    doc._.json_test2 = [1, 2, 3]
+    json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
+    new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
+    assert all([new_doc.has_extension(f"json_test{i}") for i in range(1, 3)])
+    assert new_doc._.json_test1 == "hello world"
+    assert new_doc._.json_test2 == [1, 2, 3]
+
+
+def test_json_to_doc_spans(doc):
+    """Test that Doc.from_json() includes correct.spans."""
+    doc.spans["test"] = [
+        Span(doc, 0, 2, label="test"),
+        Span(doc, 0, 1, label="test", kb_id=7),
+    ]
+    json_doc = doc.to_json()
+    new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
+    assert len(new_doc.spans) == 1
+    assert len(new_doc.spans["test"]) == 2
+    for i in range(2):
+        assert new_doc.spans["test"][i].start == doc.spans["test"][i].start
+        assert new_doc.spans["test"][i].end == doc.spans["test"][i].end
+        assert new_doc.spans["test"][i].label == doc.spans["test"][i].label
+        assert new_doc.spans["test"][i].kb_id == doc.spans["test"][i].kb_id
+
+
+def test_json_to_doc_sents(doc, doc_without_deps):
+    """Test that Doc.from_json() includes correct.sents."""
+    for test_doc in (doc, doc_without_deps):
+        json_doc = test_doc.to_json()
+        new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
+        assert [sent.text for sent in test_doc.sents] == [
+            sent.text for sent in new_doc.sents
+        ]
+        assert [token.is_sent_start for token in test_doc] == [
+            token.is_sent_start for token in new_doc
+        ]
+
+
+def test_json_to_doc_cats(doc):
+    """Test that Doc.from_json() includes correct .cats."""
+    cats = {"A": 0.3, "B": 0.7}
+    doc.cats = cats
+    json_doc = doc.to_json()
+    new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
+    assert new_doc.cats == cats
+
+
+def test_json_to_doc_spaces():
+    """Test that Doc.from_json() preserves spaces correctly."""
+    doc = spacy.blank("en")("This is just brilliant.")
+    json_doc = doc.to_json()
+    new_doc = Doc(doc.vocab).from_json(json_doc, validate=True)
+    assert doc.text == new_doc.text
+
+
+def test_json_to_doc_attribute_consistency(doc):
+    """Test that Doc.from_json() raises an exception if tokens don't all have the same set of properties."""
+    doc_json = doc.to_json()
+    doc_json["tokens"][1].pop("morph")
+    with pytest.raises(ValueError):
+        Doc(doc.vocab).from_json(doc_json)
+
+
+def test_json_to_doc_validation_error(doc):
+    """Test that Doc.from_json() raises an exception when validating invalid input."""
+    doc_json = doc.to_json()
+    doc_json.pop("tokens")
+    with pytest.raises(ValueError):
+        Doc(doc.vocab).from_json(doc_json, validate=True)

spacy/tests/doc/test_pickle_doc.py

@@ -5,11 +5,9 @@ from spacy.compat import pickle
 def test_pickle_single_doc():
     nlp = Language()
     doc = nlp("pickle roundtrip")
-    doc._context = 3
     data = pickle.dumps(doc, 1)
     doc2 = pickle.loads(data)
     assert doc2.text == "pickle roundtrip"
-    assert doc2._context == 3
 
 
 def test_list_of_docs_pickles_efficiently():

spacy/tests/doc/test_span.py

@@ -428,10 +428,19 @@ def test_span_string_label_kb_id(doc):
     assert span.kb_id == doc.vocab.strings["Q342"]
 
 
+def test_span_string_label_id(doc):
+    span = Span(doc, 0, 1, label="hello", span_id="Q342")
+    assert span.label_ == "hello"
+    assert span.label == doc.vocab.strings["hello"]
+    assert span.id_ == "Q342"
+    assert span.id == doc.vocab.strings["Q342"]
+
+
 def test_span_attrs_writable(doc):
     span = Span(doc, 0, 1)
     span.label_ = "label"
     span.kb_id_ = "kb_id"
+    span.id_ = "id"
 
 
 def test_span_ents_property(doc):
@@ -619,6 +628,9 @@ def test_span_comparison(doc):
     assert Span(doc, 0, 4, "LABEL", kb_id="KB_ID") <= Span(doc, 1, 3)
     assert Span(doc, 1, 3) > Span(doc, 0, 4, "LABEL", kb_id="KB_ID")
     assert Span(doc, 1, 3) >= Span(doc, 0, 4, "LABEL", kb_id="KB_ID")
+
+    # Different id
+    assert Span(doc, 1, 3, span_id="AAA") < Span(doc, 1, 3, span_id="BBB")
 # fmt: on
 
 

spacy/tests/doc/test_to_json.py

@@ -1,72 +0,0 @@
-import pytest
-from spacy.tokens import Doc, Span
-
-
-@pytest.fixture()
-def doc(en_vocab):
-    words = ["c", "d", "e"]
-    pos = ["VERB", "NOUN", "NOUN"]
-    tags = ["VBP", "NN", "NN"]
-    heads = [0, 0, 0]
-    deps = ["ROOT", "dobj", "dobj"]
-    ents = ["O", "B-ORG", "O"]
-    morphs = ["Feat1=A", "Feat1=B", "Feat1=A|Feat2=D"]
-    return Doc(
-        en_vocab,
-        words=words,
-        pos=pos,
-        tags=tags,
-        heads=heads,
-        deps=deps,
-        ents=ents,
-        morphs=morphs,
-    )
-
-
-def test_doc_to_json(doc):
-    json_doc = doc.to_json()
-    assert json_doc["text"] == "c d e "
-    assert len(json_doc["tokens"]) == 3
-    assert json_doc["tokens"][0]["pos"] == "VERB"
-    assert json_doc["tokens"][0]["tag"] == "VBP"
-    assert json_doc["tokens"][0]["dep"] == "ROOT"
-    assert len(json_doc["ents"]) == 1
-    assert json_doc["ents"][0]["start"] == 2  # character offset!
-    assert json_doc["ents"][0]["end"] == 3  # character offset!
-    assert json_doc["ents"][0]["label"] == "ORG"
-
-
-def test_doc_to_json_underscore(doc):
-    Doc.set_extension("json_test1", default=False)
-    Doc.set_extension("json_test2", default=False)
-    doc._.json_test1 = "hello world"
-    doc._.json_test2 = [1, 2, 3]
-    json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
-    assert "_" in json_doc
-    assert json_doc["_"]["json_test1"] == "hello world"
-    assert json_doc["_"]["json_test2"] == [1, 2, 3]
-
-
-def test_doc_to_json_underscore_error_attr(doc):
-    """Test that Doc.to_json() raises an error if a custom attribute doesn't
-    exist in the ._ space."""
-    with pytest.raises(ValueError):
-        doc.to_json(underscore=["json_test3"])
-
-
-def test_doc_to_json_underscore_error_serialize(doc):
-    """Test that Doc.to_json() raises an error if a custom attribute value
-    isn't JSON-serializable."""
-    Doc.set_extension("json_test4", method=lambda doc: doc.text)
-    with pytest.raises(ValueError):
-        doc.to_json(underscore=["json_test4"])
-
-
-def test_doc_to_json_span(doc):
-    """Test that Doc.to_json() includes spans"""
-    doc.spans["test"] = [Span(doc, 0, 2, "test"), Span(doc, 0, 1, "test")]
-    json_doc = doc.to_json()
-    assert "spans" in json_doc
-    assert len(json_doc["spans"]) == 1
-    assert len(json_doc["spans"]["test"]) == 2
-    assert json_doc["spans"]["test"][0]["start"] == 0

spacy/tests/lang/bg/test_tokenizer.py

@@ -0,0 +1,8 @@
+import pytest
+
+
+def test_bg_tokenizer_handles_final_diacritics(bg_tokenizer):
+    text = "Ня̀маше яйца̀. Ня̀маше яйца̀."
+    tokens = bg_tokenizer(text)
+    assert tokens[1].text == "яйца̀"
+    assert tokens[2].text == "."

spacy/tests/lang/en/test_tokenizer.py

@@ -167,3 +167,12 @@ def test_issue3521(en_tokenizer, word):
     tok = en_tokenizer(word)[1]
     # 'not' and 'would' should be stopwords, also in their abbreviated forms
     assert tok.is_stop
+
+
+@pytest.mark.issue(10699)
+@pytest.mark.parametrize("text", ["theses", "thisre"])
+def test_issue10699(en_tokenizer, text):
+    """Test that 'theses' and 'thisre' are excluded from the contractions
+    generated by the English tokenizer exceptions."""
+    tokens = en_tokenizer(text)
+    assert len(tokens) == 1

spacy/tests/lang/ru/test_tokenizer.py

@@ -1,3 +1,4 @@
+from string import punctuation
 import pytest
 
 
@@ -122,3 +123,36 @@ def test_ru_tokenizer_splits_bracket_period(ru_tokenizer):
     text = "(Раз, два, три, проверка)."
     tokens = ru_tokenizer(text)
     assert tokens[len(tokens) - 1].text == "."
+
+
+@pytest.mark.parametrize(
+    "text",
+    [
+        "рекоменду́я подда́ть жару́. Самого́ Баргамота",
+        "РЕКОМЕНДУ́Я ПОДДА́ТЬ ЖАРУ́. САМОГО́ БАРГАМОТА",
+        "рекоменду̍я подда̍ть жару̍.Самого̍ Баргамота",
+        "рекоменду̍я подда̍ть жару̍.'Самого̍ Баргамота",
+        "рекоменду̍я подда̍ть жару̍,самого̍ Баргамота",
+        "рекоменду̍я подда̍ть жару̍:самого̍ Баргамота",
+        "рекоменду̍я подда̍ть жару̍. самого̍ Баргамота",
+        "рекоменду̍я подда̍ть жару̍, самого̍ Баргамота",
+        "рекоменду̍я подда̍ть жару̍: самого̍ Баргамота",
+        "рекоменду̍я подда̍ть жару̍-самого̍ Баргамота",
+    ],
+)
+def test_ru_tokenizer_handles_final_diacritics(ru_tokenizer, text):
+    tokens = ru_tokenizer(text)
+    assert tokens[2].text in ("жару́", "ЖАРУ́", "жару̍")
+    assert tokens[3].text in punctuation
+
+
+@pytest.mark.parametrize(
+    "text",
+    [
+        "РЕКОМЕНДУ́Я ПОДДА́ТЬ ЖАРУ́.САМОГО́ БАРГАМОТА",
+        "рекоменду̍я подда̍ть жару́.самого́ Баргамота",
+    ],
+)
+def test_ru_tokenizer_handles_final_diacritic_and_period(ru_tokenizer, text):
+    tokens = ru_tokenizer(text)
+    assert tokens[2].text.lower() == "жару́.самого́"

spacy/tests/lang/uk/test_tokenizer.py

@@ -140,3 +140,10 @@ def test_uk_tokenizer_splits_bracket_period(uk_tokenizer):
     text = "(Раз, два, три, проверка)."
     tokens = uk_tokenizer(text)
     assert tokens[len(tokens) - 1].text == "."
+
+
+def test_uk_tokenizer_handles_final_diacritics(uk_tokenizer):
+    text = "Хлібі́в не було́. Хлібі́в не було́."
+    tokens = uk_tokenizer(text)
+    assert tokens[2].text == "було́"
+    assert tokens[3].text == "."

spacy/tests/matcher/test_dependency_matcher.py

@@ -316,6 +316,20 @@ def test_dependency_matcher_precedence_ops(en_vocab, op, num_matches):
         ("the", "brown", "$--", 0),
         ("brown", "the", "$--", 1),
         ("brown", "brown", "$--", 0),
+        ("quick", "fox", "<++", 1),
+        ("quick", "over", "<++", 0),
+        ("over", "jumped", "<++", 0),
+        ("the", "fox", "<++", 2),
+        ("brown", "fox", "<--", 0),
+        ("fox", "jumped", "<--", 0),
+        ("fox", "over", "<--", 1),
+        ("jumped", "over", ">++", 1),
+        ("fox", "lazy", ">++", 0),
+        ("over", "the", ">++", 0),
+        ("brown", "fox", ">--", 0),
+        ("fox", "brown", ">--", 1),
+        ("jumped", "fox", ">--", 1),
+        ("fox", "the", ">--", 2),
     ],
 )
 def test_dependency_matcher_ops(en_vocab, doc, left, right, op, num_matches):

spacy/tests/matcher/test_matcher_api.py

@@ -476,6 +476,17 @@ def test_matcher_extension_set_membership(en_vocab):
     assert len(matches) == 0
 
 
+@pytest.mark.xfail(reason="IN predicate must handle sequence values in extensions")
+def test_matcher_extension_in_set_predicate(en_vocab):
+    matcher = Matcher(en_vocab)
+    Token.set_extension("ext", default=[])
+    pattern = [{"_": {"ext": {"IN": ["A", "C"]}}}]
+    matcher.add("M", [pattern])
+    doc = Doc(en_vocab, words=["a", "b", "c"])
+    doc[0]._.ext = ["A", "B"]
+    assert len(matcher(doc)) == 1
+
+
 def test_matcher_basic_check(en_vocab):
     matcher = Matcher(en_vocab)
     # Potential mistake: pass in pattern instead of list of patterns
@@ -669,3 +680,38 @@ def test_matcher_ent_iob_key(en_vocab):
     assert matches[0] == "Maria"
     assert matches[1] == "Maria Esperanza"
     assert matches[2] == "Esperanza"
+
+
+def test_matcher_min_max_operator(en_vocab):
+    # Exactly n matches {n}
+    doc = Doc(
+        en_vocab,
+        words=["foo", "bar", "foo", "foo", "bar", "foo", "foo", "foo", "bar", "bar"],
+    )
+    matcher = Matcher(en_vocab)
+    pattern = [{"ORTH": "foo", "OP": "{3}"}]
+    matcher.add("TEST", [pattern])
+
+    matches1 = [doc[start:end].text for _, start, end in matcher(doc)]
+    assert len(matches1) == 1
+
+    # At least n matches {n,}
+    matcher = Matcher(en_vocab)
+    pattern = [{"ORTH": "foo", "OP": "{2,}"}]
+    matcher.add("TEST", [pattern])
+    matches2 = [doc[start:end].text for _, start, end in matcher(doc)]
+    assert len(matches2) == 4
+
+    # At most m matches {,m}
+    matcher = Matcher(en_vocab)
+    pattern = [{"ORTH": "foo", "OP": "{,2}"}]
+    matcher.add("TEST", [pattern])
+    matches3 = [doc[start:end].text for _, start, end in matcher(doc)]
+    assert len(matches3) == 9
+
+    # At least n matches and most m matches {n,m}
+    matcher = Matcher(en_vocab)
+    pattern = [{"ORTH": "foo", "OP": "{2,3}"}]
+    matcher.add("TEST", [pattern])
+    matches4 = [doc[start:end].text for _, start, end in matcher(doc)]
+    assert len(matches4) == 4

spacy/tests/matcher/test_matcher_logic.py

@@ -699,6 +699,10 @@ def test_matcher_with_alignments_greedy_longest(en_vocab):
         ("aaaa", "a a a a a?", [0, 1, 2, 3]),
         ("aaab", "a+ a b", [0, 0, 1, 2]),
         ("aaab", "a+ a+ b", [0, 0, 1, 2]),
+        ("aaab", "a{2,} b", [0, 0, 0, 1]),
+        ("aaab", "a{,3} b", [0, 0, 0, 1]),
+        ("aaab", "a{2} b", [0, 0, 1]),
+        ("aaab", "a{2,3} b", [0, 0, 0, 1]),
     ]
     for string, pattern_str, result in cases:
         matcher = Matcher(en_vocab)
@@ -711,6 +715,8 @@ def test_matcher_with_alignments_greedy_longest(en_vocab):
                 pattern.append({"ORTH": part[0], "OP": "*"})
             elif part.endswith("?"):
                 pattern.append({"ORTH": part[0], "OP": "?"})
+            elif part.endswith("}"):
+                pattern.append({"ORTH": part[0], "OP": part[1:]})
             else:
                 pattern.append({"ORTH": part})
         matcher.add("PATTERN", [pattern], greedy="LONGEST")
@@ -722,7 +728,7 @@ def test_matcher_with_alignments_greedy_longest(en_vocab):
         assert expected == result, (string, pattern_str, s, e, n_matches)
 
 
-def test_matcher_with_alignments_nongreedy(en_vocab):
+def test_matcher_with_alignments_non_greedy(en_vocab):
     cases = [
         (0, "aaab", "a* b", [[0, 1], [0, 0, 1], [0, 0, 0, 1], [1]]),
         (1, "baab", "b a* b", [[0, 1, 1, 2]]),
@@ -752,6 +758,10 @@ def test_matcher_with_alignments_nongreedy(en_vocab):
         (15, "aaaa", "a a a a a?", [[0, 1, 2, 3]]),
         (16, "aaab", "a+ a b", [[0, 1, 2], [0, 0, 1, 2]]),
         (17, "aaab", "a+ a+ b", [[0, 1, 2], [0, 0, 1, 2]]),
+        (18, "aaab", "a{2,} b", [[0, 0, 1], [0, 0, 0, 1]]),
+        (19, "aaab", "a{3} b", [[0, 0, 0, 1]]),
+        (20, "aaab", "a{2} b", [[0, 0, 1]]),
+        (21, "aaab", "a{2,3} b", [[0, 0, 1], [0, 0, 0, 1]]),
     ]
     for case_id, string, pattern_str, results in cases:
         matcher = Matcher(en_vocab)
@@ -764,6 +774,8 @@ def test_matcher_with_alignments_nongreedy(en_vocab):
                 pattern.append({"ORTH": part[0], "OP": "*"})
             elif part.endswith("?"):
                 pattern.append({"ORTH": part[0], "OP": "?"})
+            elif part.endswith("}"):
+                pattern.append({"ORTH": part[0], "OP": part[1:]})
             else:
                 pattern.append({"ORTH": part})
 

spacy/tests/matcher/test_pattern_validation.py

@@ -14,6 +14,14 @@ TEST_PATTERNS = [
     ('[{"TEXT": "foo"}, {"LOWER": "bar"}]', 1, 1),
     ([{"ENT_IOB": "foo"}], 1, 1),
     ([1, 2, 3], 3, 1),
+    ([{"TEXT": "foo", "OP": "{,}"}], 1, 1),
+    ([{"TEXT": "foo", "OP": "{,4}4"}], 1, 1),
+    ([{"TEXT": "foo", "OP": "{a,3}"}], 1, 1),
+    ([{"TEXT": "foo", "OP": "{a}"}], 1, 1),
+    ([{"TEXT": "foo", "OP": "{,a}"}], 1, 1),
+    ([{"TEXT": "foo", "OP": "{1,2,3}"}], 1, 1),
+    ([{"TEXT": "foo", "OP": "{1, 3}"}], 1, 1),
+    ([{"TEXT": "foo", "OP": "{-2}"}], 1, 1),
     # Bad patterns flagged outside of Matcher
     ([{"_": {"foo": "bar", "baz": {"IN": "foo"}}}], 2, 0),  # prev: (1, 0)
     # Bad patterns not flagged with minimal checks
@@ -38,6 +46,7 @@ TEST_PATTERNS = [
     ([{"SENT_START": True}], 0, 0),
     ([{"ENT_ID": "STRING"}], 0, 0),
     ([{"ENT_KB_ID": "STRING"}], 0, 0),
+    ([{"TEXT": "ha", "OP": "{3}"}], 0, 0),
 ]
 
 

spacy/tests/matcher/test_phrase_matcher.py

@@ -122,6 +122,36 @@ def test_issue6839(en_vocab):
     assert matches
 
 
+@pytest.mark.issue(10643)
+def test_issue10643(en_vocab):
+    """Ensure overlapping terms can be removed from PhraseMatcher"""
+
+    # fmt: off
+    words = ["Only", "save", "out", "the", "binary", "data", "for", "the", "individual", "components", "."]
+    # fmt: on
+    doc = Doc(en_vocab, words=words)
+    terms = {
+        "0": Doc(en_vocab, words=["binary"]),
+        "1": Doc(en_vocab, words=["binary", "data"]),
+    }
+    matcher = PhraseMatcher(en_vocab)
+    for match_id, term in terms.items():
+        matcher.add(match_id, [term])
+
+    matches = matcher(doc)
+    assert matches == [(en_vocab.strings["0"], 4, 5), (en_vocab.strings["1"], 4, 6)]
+
+    matcher.remove("0")
+    assert len(matcher) == 1
+    new_matches = matcher(doc)
+    assert new_matches == [(en_vocab.strings["1"], 4, 6)]
+
+    matcher.remove("1")
+    assert len(matcher) == 0
+    no_matches = matcher(doc)
+    assert not no_matches
+
+
 def test_matcher_phrase_matcher(en_vocab):
     doc = Doc(en_vocab, words=["I", "like", "Google", "Now", "best"])
     # intermediate phrase

spacy/tests/parser/test_ner.py

@@ -10,7 +10,7 @@ from spacy.lang.it import Italian
 from spacy.language import Language
 from spacy.lookups import Lookups
 from spacy.pipeline._parser_internals.ner import BiluoPushDown
-from spacy.training import Example, iob_to_biluo
+from spacy.training import Example, iob_to_biluo, split_bilu_label
 from spacy.tokens import Doc, Span
 from spacy.vocab import Vocab
 import logging
@@ -110,6 +110,9 @@ def test_issue2385():
     # maintain support for iob2 format
     tags3 = ("B-PERSON", "I-PERSON", "B-PERSON")
     assert iob_to_biluo(tags3) == ["B-PERSON", "L-PERSON", "U-PERSON"]
+    # ensure it works with hyphens in the name
+    tags4 = ("B-MULTI-PERSON", "I-MULTI-PERSON", "B-MULTI-PERSON")
+    assert iob_to_biluo(tags4) == ["B-MULTI-PERSON", "L-MULTI-PERSON", "U-MULTI-PERSON"]
 
 
 @pytest.mark.issue(2800)
@@ -154,6 +157,24 @@ def test_issue3209():
     assert ner2.move_names == move_names
 
 
+def test_labels_from_BILUO():
+    """Test that labels are inferred correctly when there's a - in label."""
+    nlp = English()
+    ner = nlp.add_pipe("ner")
+    ner.add_label("LARGE-ANIMAL")
+    nlp.initialize()
+    move_names = [
+        "O",
+        "B-LARGE-ANIMAL",
+        "I-LARGE-ANIMAL",
+        "L-LARGE-ANIMAL",
+        "U-LARGE-ANIMAL",
+    ]
+    labels = {"LARGE-ANIMAL"}
+    assert ner.move_names == move_names
+    assert set(ner.labels) == labels
+
+
 @pytest.mark.issue(4267)
 def test_issue4267():
     """Test that running an entity_ruler after ner gives consistent results"""
@@ -298,7 +319,7 @@ def test_oracle_moves_missing_B(en_vocab):
         elif tag == "O":
             moves.add_action(move_types.index("O"), "")
         else:
-            action, label = tag.split("-")
+            action, label = split_bilu_label(tag)
             moves.add_action(move_types.index("B"), label)
             moves.add_action(move_types.index("I"), label)
             moves.add_action(move_types.index("L"), label)
@@ -324,7 +345,7 @@ def test_oracle_moves_whitespace(en_vocab):
         elif tag == "O":
             moves.add_action(move_types.index("O"), "")
         else:
-            action, label = tag.split("-")
+            action, label = split_bilu_label(tag)
             moves.add_action(move_types.index(action), label)
     moves.get_oracle_sequence(example)
 

spacy/tests/parser/test_nonproj.py

@@ -49,7 +49,9 @@ def test_parser_contains_cycle(tree, cyclic_tree, partial_tree, multirooted_tree
     assert contains_cycle(multirooted_tree) is None
 
 
-def test_parser_is_nonproj_arc(nonproj_tree, partial_tree, multirooted_tree):
+def test_parser_is_nonproj_arc(
+    cyclic_tree, nonproj_tree, partial_tree, multirooted_tree
+):
     assert is_nonproj_arc(0, nonproj_tree) is False
     assert is_nonproj_arc(1, nonproj_tree) is False
     assert is_nonproj_arc(2, nonproj_tree) is False
@@ -62,15 +64,23 @@ def test_parser_is_nonproj_arc(nonproj_tree, partial_tree, multirooted_tree):
     assert is_nonproj_arc(7, partial_tree) is False
     assert is_nonproj_arc(17, multirooted_tree) is False
     assert is_nonproj_arc(16, multirooted_tree) is True
+    with pytest.raises(
+        ValueError, match=r"Found cycle in dependency graph: \[1, 2, 2, 4, 5, 3, 2\]"
+    ):
+        is_nonproj_arc(6, cyclic_tree)
 
 
 def test_parser_is_nonproj_tree(
-    proj_tree, nonproj_tree, partial_tree, multirooted_tree
+    proj_tree, cyclic_tree, nonproj_tree, partial_tree, multirooted_tree
 ):
     assert is_nonproj_tree(proj_tree) is False
     assert is_nonproj_tree(nonproj_tree) is True
     assert is_nonproj_tree(partial_tree) is False
     assert is_nonproj_tree(multirooted_tree) is True
+    with pytest.raises(
+        ValueError, match=r"Found cycle in dependency graph: \[1, 2, 2, 4, 5, 3, 2\]"
+    ):
+        is_nonproj_tree(cyclic_tree)
 
 
 def test_parser_pseudoprojectivity(en_vocab):
@@ -84,8 +94,10 @@ def test_parser_pseudoprojectivity(en_vocab):
     tree = [1, 2, 2]
     nonproj_tree = [1, 2, 2, 4, 5, 2, 7, 4, 2]
     nonproj_tree2 = [9, 1, 3, 1, 5, 6, 9, 8, 6, 1, 6, 12, 13, 10, 1]
+    cyclic_tree = [1, 2, 2, 4, 5, 3, 2]
     labels = ["det", "nsubj", "root", "det", "dobj", "aux", "nsubj", "acl", "punct"]
     labels2 = ["advmod", "root", "det", "nsubj", "advmod", "det", "dobj", "det", "nmod", "aux", "nmod", "advmod", "det", "amod", "punct"]
+    cyclic_labels = ["det", "nsubj", "root", "det", "dobj", "aux", "punct"]
     # fmt: on
     assert nonproj.decompose("X||Y") == ("X", "Y")
     assert nonproj.decompose("X") == ("X", "")
@@ -97,6 +109,8 @@ def test_parser_pseudoprojectivity(en_vocab):
     assert nonproj.get_smallest_nonproj_arc_slow(nonproj_tree2) == 10
     # fmt: off
     proj_heads, deco_labels = nonproj.projectivize(nonproj_tree, labels)
+    with pytest.raises(ValueError, match=r'Found cycle in dependency graph: \[1, 2, 2, 4, 5, 3, 2\]'):
+        nonproj.projectivize(cyclic_tree, cyclic_labels)
     assert proj_heads == [1, 2, 2, 4, 5, 2, 7, 5, 2]
     assert deco_labels == ["det", "nsubj", "root", "det", "dobj", "aux",
                            "nsubj", "acl||dobj", "punct"]

spacy/tests/parser/test_parse.py

@@ -12,6 +12,7 @@ from spacy.vocab import Vocab
 from ...pipeline import DependencyParser
 from ...pipeline.dep_parser import DEFAULT_PARSER_MODEL
 from ..util import apply_transition_sequence, make_tempdir
+from ...pipeline.tok2vec import DEFAULT_TOK2VEC_MODEL
 
 TRAIN_DATA = [
     (
@@ -395,6 +396,34 @@ def test_overfitting_IO(pipe_name):
     assert_equal(batch_deps_1, no_batch_deps)
 
 
+# fmt: off
+@pytest.mark.slow
+@pytest.mark.parametrize("pipe_name", ["parser", "beam_parser"])
+@pytest.mark.parametrize(
+    "parser_config",
+    [
+        # TransitionBasedParser V1
+        ({"@architectures": "spacy.TransitionBasedParser.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "state_type": "parser", "extra_state_tokens": False, "hidden_width": 64, "maxout_pieces": 2, "use_upper": True}),
+        # TransitionBasedParser V2
+        ({"@architectures": "spacy.TransitionBasedParser.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "state_type": "parser", "extra_state_tokens": False, "hidden_width": 64, "maxout_pieces": 2, "use_upper": True}),
+    ],
+)
+# fmt: on
+def test_parser_configs(pipe_name, parser_config):
+    pipe_config = {"model": parser_config}
+    nlp = English()
+    parser = nlp.add_pipe(pipe_name, config=pipe_config)
+    train_examples = []
+    for text, annotations in TRAIN_DATA:
+        train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
+        for dep in annotations.get("deps", []):
+            parser.add_label(dep)
+    optimizer = nlp.initialize()
+    for i in range(5):
+        losses = {}
+        nlp.update(train_examples, sgd=optimizer, losses=losses)
+
+
 def test_beam_parser_scores():
     # Test that we can get confidence values out of the beam_parser pipe
     beam_width = 16

spacy/tests/pipeline/test_entity_linker.py

@@ -1,4 +1,4 @@
-from typing import Callable, Iterable
+from typing import Callable, Iterable, Dict, Any
 
 import pytest
 from numpy.testing import assert_equal
@@ -14,7 +14,7 @@ from spacy.pipeline.legacy import EntityLinker_v1
 from spacy.pipeline.tok2vec import DEFAULT_TOK2VEC_MODEL
 from spacy.scorer import Scorer
 from spacy.tests.util import make_tempdir
-from spacy.tokens import Span
+from spacy.tokens import Span, Doc
 from spacy.training import Example
 from spacy.util import ensure_path
 from spacy.vocab import Vocab
@@ -207,7 +207,7 @@ def test_no_entities():
     nlp.add_pipe("sentencizer", first=True)
 
     # this will run the pipeline on the examples and shouldn't crash
-    results = nlp.evaluate(train_examples)
+    nlp.evaluate(train_examples)
 
 
 def test_partial_links():
@@ -1063,7 +1063,7 @@ def test_no_gold_ents(patterns):
         "entity_linker", config={"use_gold_ents": False}, last=True
     )
     entity_linker.set_kb(create_kb)
-    assert entity_linker.use_gold_ents == False
+    assert entity_linker.use_gold_ents is False
 
     optimizer = nlp.initialize(get_examples=lambda: train_examples)
     for i in range(2):
@@ -1074,4 +1074,101 @@ def test_no_gold_ents(patterns):
     nlp.add_pipe("sentencizer", first=True)
 
     # this will run the pipeline on the examples and shouldn't crash
-    results = nlp.evaluate(train_examples)
+    nlp.evaluate(train_examples)
+
+
+@pytest.mark.issue(9575)
+def test_tokenization_mismatch():
+    nlp = English()
+    # include a matching entity so that update isn't skipped
+    doc1 = Doc(
+        nlp.vocab,
+        words=["Kirby", "123456"],
+        spaces=[True, False],
+        ents=["B-CHARACTER", "B-CARDINAL"],
+    )
+    doc2 = Doc(
+        nlp.vocab,
+        words=["Kirby", "123", "456"],
+        spaces=[True, False, False],
+        ents=["B-CHARACTER", "B-CARDINAL", "B-CARDINAL"],
+    )
+
+    eg = Example(doc1, doc2)
+    train_examples = [eg]
+    vector_length = 3
+
+    def create_kb(vocab):
+        # create placeholder KB
+        mykb = KnowledgeBase(vocab, entity_vector_length=vector_length)
+        mykb.add_entity(entity="Q613241", freq=12, entity_vector=[6, -4, 3])
+        mykb.add_alias("Kirby", ["Q613241"], [0.9])
+        return mykb
+
+    entity_linker = nlp.add_pipe("entity_linker", last=True)
+    entity_linker.set_kb(create_kb)
+
+    optimizer = nlp.initialize(get_examples=lambda: train_examples)
+    for i in range(2):
+        losses = {}
+        nlp.update(train_examples, sgd=optimizer, losses=losses)
+
+    nlp.add_pipe("sentencizer", first=True)
+    nlp.evaluate(train_examples)
+
+
+# fmt: off
+@pytest.mark.parametrize(
+    "meet_threshold,config",
+    [
+        (False, {"@architectures": "spacy.EntityLinker.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL}),
+        (True, {"@architectures": "spacy.EntityLinker.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL}),
+    ],
+)
+# fmt: on
+def test_threshold(meet_threshold: bool, config: Dict[str, Any]):
+    """Tests abstention threshold.
+    meet_threshold (bool): Whether to configure NEL setup so that confidence threshold is met.
+    config (Dict[str, Any]): NEL architecture config.
+    """
+    nlp = English()
+    nlp.add_pipe("sentencizer")
+    text = "Mahler's Symphony No. 8 was beautiful."
+    entities = [(0, 6, "PERSON")]
+    links = {(0, 6): {"Q7304": 1.0}}
+    sent_starts = [1, -1, 0, 0, 0, 0, 0, 0, 0]
+    entity_id = "Q7304"
+    doc = nlp(text)
+    train_examples = [
+        Example.from_dict(
+            doc, {"entities": entities, "links": links, "sent_starts": sent_starts}
+        )
+    ]
+
+    def create_kb(vocab):
+        # create artificial KB
+        mykb = KnowledgeBase(vocab, entity_vector_length=3)
+        mykb.add_entity(entity=entity_id, freq=12, entity_vector=[6, -4, 3])
+        mykb.add_alias(
+            alias="Mahler",
+            entities=[entity_id],
+            probabilities=[1 if meet_threshold else 0.01],
+        )
+        return mykb
+
+    # Create the Entity Linker component and add it to the pipeline
+    entity_linker = nlp.add_pipe(
+        "entity_linker",
+        last=True,
+        config={"threshold": 0.99, "model": config},
+    )
+    entity_linker.set_kb(create_kb)  # type: ignore
+    nlp.initialize(get_examples=lambda: train_examples)
+
+    # Add a custom rule-based component to mimick NER
+    ruler = nlp.add_pipe("entity_ruler", before="entity_linker")
+    ruler.add_patterns([{"label": "PERSON", "pattern": [{"LOWER": "mahler"}]}])  # type: ignore
+    doc = nlp(text)
+
+    assert len(doc.ents) == 1
+    assert doc.ents[0].kb_id_ == entity_id if meet_threshold else EntityLinker.NIL

spacy/tests/pipeline/test_entity_ruler.py

@@ -5,12 +5,15 @@ from spacy.tokens import Doc, Span
 from spacy.language import Language
 from spacy.lang.en import English
 from spacy.pipeline import EntityRuler, EntityRecognizer, merge_entities
+from spacy.pipeline import SpanRuler
 from spacy.pipeline.ner import DEFAULT_NER_MODEL
 from spacy.errors import MatchPatternError
 from spacy.tests.util import make_tempdir
 
 from thinc.api import NumpyOps, get_current_ops
 
+ENTITY_RULERS = ["entity_ruler", "future_entity_ruler"]
+
 
 @pytest.fixture
 def nlp():
@@ -37,12 +40,14 @@ def add_ent_component(doc):
 
 
 @pytest.mark.issue(3345)
-def test_issue3345():
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_issue3345(entity_ruler_factory):
     """Test case where preset entity crosses sentence boundary."""
     nlp = English()
     doc = Doc(nlp.vocab, words=["I", "live", "in", "New", "York"])
     doc[4].is_sent_start = True
-    ruler = EntityRuler(nlp, patterns=[{"label": "GPE", "pattern": "New York"}])
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
+    ruler.add_patterns([{"label": "GPE", "pattern": "New York"}])
     cfg = {"model": DEFAULT_NER_MODEL}
     model = registry.resolve(cfg, validate=True)["model"]
     ner = EntityRecognizer(doc.vocab, model)
@@ -60,13 +65,18 @@ def test_issue3345():
 
 
 @pytest.mark.issue(4849)
-def test_issue4849():
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_issue4849(entity_ruler_factory):
     nlp = English()
     patterns = [
         {"label": "PERSON", "pattern": "joe biden", "id": "joe-biden"},
         {"label": "PERSON", "pattern": "bernie sanders", "id": "bernie-sanders"},
     ]
-    ruler = nlp.add_pipe("entity_ruler", config={"phrase_matcher_attr": "LOWER"})
+    ruler = nlp.add_pipe(
+        entity_ruler_factory,
+        name="entity_ruler",
+        config={"phrase_matcher_attr": "LOWER"},
+    )
     ruler.add_patterns(patterns)
     text = """
     The left is starting to take aim at Democratic front-runner Joe Biden.
@@ -86,10 +96,11 @@ def test_issue4849():
 
 
 @pytest.mark.issue(5918)
-def test_issue5918():
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_issue5918(entity_ruler_factory):
     # Test edge case when merging entities.
     nlp = English()
-    ruler = nlp.add_pipe("entity_ruler")
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
         {"label": "ORG", "pattern": "Digicon Inc"},
         {"label": "ORG", "pattern": "Rotan Mosle Inc's"},
@@ -114,9 +125,10 @@ def test_issue5918():
 
 
 @pytest.mark.issue(8168)
-def test_issue8168():
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_issue8168(entity_ruler_factory):
     nlp = English()
-    ruler = nlp.add_pipe("entity_ruler")
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
         {"label": "ORG", "pattern": "Apple"},
         {
@@ -131,14 +143,17 @@ def test_issue8168():
         },
     ]
     ruler.add_patterns(patterns)
-
+    doc = nlp("San Francisco San Fran")
-    assert ruler._ent_ids == {8043148519967183733: ("GPE", "san-francisco")}
+    assert all(t.ent_id_ == "san-francisco" for t in doc)
 
 
 @pytest.mark.issue(8216)
-def test_entity_ruler_fix8216(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_fix8216(nlp, patterns, entity_ruler_factory):
     """Test that patterns don't get added excessively."""
-    ruler = nlp.add_pipe("entity_ruler", config={"validate": True})
+    ruler = nlp.add_pipe(
+        entity_ruler_factory, name="entity_ruler", config={"validate": True}
+    )
     ruler.add_patterns(patterns)
     pattern_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
     assert pattern_count > 0
@@ -147,13 +162,16 @@ def test_entity_ruler_fix8216(nlp, patterns):
     assert after_count == pattern_count
 
 
-def test_entity_ruler_init(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp, patterns=patterns)
+def test_entity_ruler_init(nlp, patterns, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
+    ruler.add_patterns(patterns)
     assert len(ruler) == len(patterns)
     assert len(ruler.labels) == 4
     assert "HELLO" in ruler
     assert "BYE" in ruler
-    ruler = nlp.add_pipe("entity_ruler")
+    nlp.remove_pipe("entity_ruler")
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     ruler.add_patterns(patterns)
     doc = nlp("hello world bye bye")
     assert len(doc.ents) == 2
@@ -161,20 +179,23 @@ def test_entity_ruler_init(nlp, patterns):
     assert doc.ents[1].label_ == "BYE"
 
 
-def test_entity_ruler_no_patterns_warns(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_no_patterns_warns(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     assert len(ruler) == 0
     assert len(ruler.labels) == 0
-    nlp.add_pipe("entity_ruler")
+    nlp.remove_pipe("entity_ruler")
+    nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     assert nlp.pipe_names == ["entity_ruler"]
     with pytest.warns(UserWarning):
         doc = nlp("hello world bye bye")
     assert len(doc.ents) == 0
 
 
-def test_entity_ruler_init_patterns(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_init_patterns(nlp, patterns, entity_ruler_factory):
     # initialize with patterns
-    ruler = nlp.add_pipe("entity_ruler")
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     assert len(ruler.labels) == 0
     ruler.initialize(lambda: [], patterns=patterns)
     assert len(ruler.labels) == 4
@@ -186,7 +207,7 @@ def test_entity_ruler_init_patterns(nlp, patterns):
     nlp.config["initialize"]["components"]["entity_ruler"] = {
         "patterns": {"@misc": "entity_ruler_patterns"}
     }
-    ruler = nlp.add_pipe("entity_ruler")
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     assert len(ruler.labels) == 0
     nlp.initialize()
     assert len(ruler.labels) == 4
@@ -195,18 +216,20 @@ def test_entity_ruler_init_patterns(nlp, patterns):
     assert doc.ents[1].label_ == "BYE"
 
 
-def test_entity_ruler_init_clear(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_init_clear(nlp, patterns, entity_ruler_factory):
     """Test that initialization clears patterns."""
-    ruler = nlp.add_pipe("entity_ruler")
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     ruler.add_patterns(patterns)
     assert len(ruler.labels) == 4
     ruler.initialize(lambda: [])
     assert len(ruler.labels) == 0
 
 
-def test_entity_ruler_clear(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_clear(nlp, patterns, entity_ruler_factory):
     """Test that initialization clears patterns."""
-    ruler = nlp.add_pipe("entity_ruler")
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     ruler.add_patterns(patterns)
     assert len(ruler.labels) == 4
     doc = nlp("hello world")
@@ -218,8 +241,9 @@ def test_entity_ruler_clear(nlp, patterns):
     assert len(doc.ents) == 0
 
 
-def test_entity_ruler_existing(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = nlp.add_pipe("entity_ruler")
+def test_entity_ruler_existing(nlp, patterns, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     ruler.add_patterns(patterns)
     nlp.add_pipe("add_ent", before="entity_ruler")
     doc = nlp("OH HELLO WORLD bye bye")
@@ -228,8 +252,11 @@ def test_entity_ruler_existing(nlp, patterns):
     assert doc.ents[1].label_ == "BYE"
 
 
-def test_entity_ruler_existing_overwrite(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
+def test_entity_ruler_existing_overwrite(nlp, patterns, entity_ruler_factory):
+    ruler = nlp.add_pipe(
+        entity_ruler_factory, name="entity_ruler", config={"overwrite_ents": True}
+    )
     ruler.add_patterns(patterns)
     nlp.add_pipe("add_ent", before="entity_ruler")
     doc = nlp("OH HELLO WORLD bye bye")
@@ -239,8 +266,11 @@ def test_entity_ruler_existing_overwrite(nlp, patterns):
     assert doc.ents[1].label_ == "BYE"
 
 
-def test_entity_ruler_existing_complex(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
+def test_entity_ruler_existing_complex(nlp, patterns, entity_ruler_factory):
+    ruler = nlp.add_pipe(
+        entity_ruler_factory, name="entity_ruler", config={"overwrite_ents": True}
+    )
     ruler.add_patterns(patterns)
     nlp.add_pipe("add_ent", before="entity_ruler")
     doc = nlp("foo foo bye bye")
@@ -251,8 +281,11 @@ def test_entity_ruler_existing_complex(nlp, patterns):
     assert len(doc.ents[1]) == 2
 
 
-def test_entity_ruler_entity_id(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
+def test_entity_ruler_entity_id(nlp, patterns, entity_ruler_factory):
+    ruler = nlp.add_pipe(
+        entity_ruler_factory, name="entity_ruler", config={"overwrite_ents": True}
+    )
     ruler.add_patterns(patterns)
     doc = nlp("Apple is a technology company")
     assert len(doc.ents) == 1
@@ -260,18 +293,21 @@ def test_entity_ruler_entity_id(nlp, patterns):
     assert doc.ents[0].ent_id_ == "a1"
 
 
-def test_entity_ruler_cfg_ent_id_sep(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_cfg_ent_id_sep(nlp, patterns, entity_ruler_factory):
     config = {"overwrite_ents": True, "ent_id_sep": "**"}
-    ruler = nlp.add_pipe("entity_ruler", config=config)
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler", config=config)
     ruler.add_patterns(patterns)
-    assert "TECH_ORG**a1" in ruler.phrase_patterns
     doc = nlp("Apple is a technology company")
+    if isinstance(ruler, EntityRuler):
+        assert "TECH_ORG**a1" in ruler.phrase_patterns
     assert len(doc.ents) == 1
     assert doc.ents[0].label_ == "TECH_ORG"
     assert doc.ents[0].ent_id_ == "a1"
 
 
-def test_entity_ruler_serialize_bytes(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_serialize_bytes(nlp, patterns, entity_ruler_factory):
     ruler = EntityRuler(nlp, patterns=patterns)
     assert len(ruler) == len(patterns)
     assert len(ruler.labels) == 4
@@ -288,7 +324,10 @@ def test_entity_ruler_serialize_bytes(nlp, patterns):
     assert sorted(new_ruler.labels) == sorted(ruler.labels)
 
 
-def test_entity_ruler_serialize_phrase_matcher_attr_bytes(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_serialize_phrase_matcher_attr_bytes(
+    nlp, patterns, entity_ruler_factory
+):
     ruler = EntityRuler(nlp, phrase_matcher_attr="LOWER", patterns=patterns)
     assert len(ruler) == len(patterns)
     assert len(ruler.labels) == 4
@@ -303,8 +342,9 @@ def test_entity_ruler_serialize_phrase_matcher_attr_bytes(nlp, patterns):
     assert new_ruler.phrase_matcher_attr == "LOWER"
 
 
-def test_entity_ruler_validate(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_validate(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     validated_ruler = EntityRuler(nlp, validate=True)
 
     valid_pattern = {"label": "HELLO", "pattern": [{"LOWER": "HELLO"}]}
@@ -322,32 +362,35 @@ def test_entity_ruler_validate(nlp):
         validated_ruler.add_patterns([invalid_pattern])
 
 
-def test_entity_ruler_properties(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_properties(nlp, patterns, entity_ruler_factory):
     ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
     assert sorted(ruler.labels) == sorted(["HELLO", "BYE", "COMPLEX", "TECH_ORG"])
     assert sorted(ruler.ent_ids) == ["a1", "a2"]
 
 
-def test_entity_ruler_overlapping_spans(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_overlapping_spans(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
         {"label": "FOOBAR", "pattern": "foo bar"},
         {"label": "BARBAZ", "pattern": "bar baz"},
     ]
     ruler.add_patterns(patterns)
-    doc = ruler(nlp.make_doc("foo bar baz"))
+    doc = nlp("foo bar baz")
     assert len(doc.ents) == 1
     assert doc.ents[0].label_ == "FOOBAR"
 
 
 @pytest.mark.parametrize("n_process", [1, 2])
-def test_entity_ruler_multiprocessing(nlp, n_process):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
+def test_entity_ruler_multiprocessing(nlp, n_process, entity_ruler_factory):
     if isinstance(get_current_ops, NumpyOps) or n_process < 2:
         texts = ["I enjoy eating Pizza Hut pizza."]
 
         patterns = [{"label": "FASTFOOD", "pattern": "Pizza Hut", "id": "1234"}]
 
-        ruler = nlp.add_pipe("entity_ruler")
+        ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
         ruler.add_patterns(patterns)
 
         for doc in nlp.pipe(texts, n_process=2):
@@ -355,8 +398,9 @@ def test_entity_ruler_multiprocessing(nlp, n_process):
                 assert ent.ent_id_ == "1234"
 
 
-def test_entity_ruler_serialize_jsonl(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = nlp.add_pipe("entity_ruler")
+def test_entity_ruler_serialize_jsonl(nlp, patterns, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     ruler.add_patterns(patterns)
     with make_tempdir() as d:
         ruler.to_disk(d / "test_ruler.jsonl")
@@ -365,8 +409,9 @@ def test_entity_ruler_serialize_jsonl(nlp, patterns):
             ruler.from_disk(d / "non_existing.jsonl")  # read from a bad jsonl file
 
 
-def test_entity_ruler_serialize_dir(nlp, patterns):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = nlp.add_pipe("entity_ruler")
+def test_entity_ruler_serialize_dir(nlp, patterns, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     ruler.add_patterns(patterns)
     with make_tempdir() as d:
         ruler.to_disk(d / "test_ruler")
@@ -375,52 +420,65 @@ def test_entity_ruler_serialize_dir(nlp, patterns):
             ruler.from_disk(d / "non_existing_dir")  # read from a bad directory
 
 
-def test_entity_ruler_remove_basic(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_remove_basic(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
-        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "PERSON", "pattern": "Dina", "id": "dina"},
         {"label": "ORG", "pattern": "ACME", "id": "acme"},
         {"label": "ORG", "pattern": "ACM"},
     ]
     ruler.add_patterns(patterns)
-    doc = ruler(nlp.make_doc("Duygu went to school"))
+    doc = nlp("Dina went to school")
     assert len(ruler.patterns) == 3
     assert len(doc.ents) == 1
+    if isinstance(ruler, EntityRuler):
+        assert "PERSON||dina" in ruler.phrase_matcher
     assert doc.ents[0].label_ == "PERSON"
-    assert doc.ents[0].text == "Duygu"
+    assert doc.ents[0].text == "Dina"
-    assert "PERSON||duygu" in ruler.phrase_matcher
+    if isinstance(ruler, EntityRuler):
-    ruler.remove("duygu")
+        ruler.remove("dina")
-    doc = ruler(nlp.make_doc("Duygu went to school"))
+    else:
+        ruler.remove_by_id("dina")
+    doc = nlp("Dina went to school")
     assert len(doc.ents) == 0
-    assert "PERSON||duygu" not in ruler.phrase_matcher
+    if isinstance(ruler, EntityRuler):
+        assert "PERSON||dina" not in ruler.phrase_matcher
     assert len(ruler.patterns) == 2
 
 
-def test_entity_ruler_remove_same_id_multiple_patterns(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_remove_same_id_multiple_patterns(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
-        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "PERSON", "pattern": "Dina", "id": "dina"},
-        {"label": "ORG", "pattern": "DuyguCorp", "id": "duygu"},
+        {"label": "ORG", "pattern": "DinaCorp", "id": "dina"},
         {"label": "ORG", "pattern": "ACME", "id": "acme"},
     ]
     ruler.add_patterns(patterns)
-    doc = ruler(nlp.make_doc("Duygu founded DuyguCorp and ACME."))
+    doc = nlp("Dina founded DinaCorp and ACME.")
     assert len(ruler.patterns) == 3
-    assert "PERSON||duygu" in ruler.phrase_matcher
+    if isinstance(ruler, EntityRuler):
-    assert "ORG||duygu" in ruler.phrase_matcher
+        assert "PERSON||dina" in ruler.phrase_matcher
+        assert "ORG||dina" in ruler.phrase_matcher
     assert len(doc.ents) == 3
-    ruler.remove("duygu")
+    if isinstance(ruler, EntityRuler):
-    doc = ruler(nlp.make_doc("Duygu founded DuyguCorp and ACME."))
+        ruler.remove("dina")
+    else:
+        ruler.remove_by_id("dina")
+    doc = nlp("Dina founded DinaCorp and ACME.")
     assert len(ruler.patterns) == 1
-    assert "PERSON||duygu" not in ruler.phrase_matcher
+    if isinstance(ruler, EntityRuler):
-    assert "ORG||duygu" not in ruler.phrase_matcher
+        assert "PERSON||dina" not in ruler.phrase_matcher
+        assert "ORG||dina" not in ruler.phrase_matcher
     assert len(doc.ents) == 1
 
 
-def test_entity_ruler_remove_nonexisting_pattern(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_remove_nonexisting_pattern(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
-        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "PERSON", "pattern": "Dina", "id": "dina"},
         {"label": "ORG", "pattern": "ACME", "id": "acme"},
         {"label": "ORG", "pattern": "ACM"},
     ]
@@ -428,82 +486,108 @@ def test_entity_ruler_remove_nonexisting_pattern(nlp):
     assert len(ruler.patterns) == 3
     with pytest.raises(ValueError):
         ruler.remove("nepattern")
-        assert len(ruler.patterns) == 3
+    if isinstance(ruler, SpanRuler):
+        with pytest.raises(ValueError):
+            ruler.remove_by_id("nepattern")
 
 
-def test_entity_ruler_remove_several_patterns(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_remove_several_patterns(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
-        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "PERSON", "pattern": "Dina", "id": "dina"},
         {"label": "ORG", "pattern": "ACME", "id": "acme"},
         {"label": "ORG", "pattern": "ACM"},
     ]
     ruler.add_patterns(patterns)
-    doc = ruler(nlp.make_doc("Duygu founded her company ACME."))
+    doc = nlp("Dina founded her company ACME.")
     assert len(ruler.patterns) == 3
     assert len(doc.ents) == 2
     assert doc.ents[0].label_ == "PERSON"
-    assert doc.ents[0].text == "Duygu"
+    assert doc.ents[0].text == "Dina"
     assert doc.ents[1].label_ == "ORG"
     assert doc.ents[1].text == "ACME"
-    ruler.remove("duygu")
+    if isinstance(ruler, EntityRuler):
-    doc = ruler(nlp.make_doc("Duygu founded her company ACME"))
+        ruler.remove("dina")
+    else:
+        ruler.remove_by_id("dina")
+    doc = nlp("Dina founded her company ACME")
     assert len(ruler.patterns) == 2
     assert len(doc.ents) == 1
     assert doc.ents[0].label_ == "ORG"
     assert doc.ents[0].text == "ACME"
+    if isinstance(ruler, EntityRuler):
         ruler.remove("acme")
-    doc = ruler(nlp.make_doc("Duygu founded her company ACME"))
+    else:
+        ruler.remove_by_id("acme")
+    doc = nlp("Dina founded her company ACME")
     assert len(ruler.patterns) == 1
     assert len(doc.ents) == 0
 
 
-def test_entity_ruler_remove_patterns_in_a_row(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_remove_patterns_in_a_row(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
-        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "PERSON", "pattern": "Dina", "id": "dina"},
         {"label": "ORG", "pattern": "ACME", "id": "acme"},
         {"label": "DATE", "pattern": "her birthday", "id": "bday"},
         {"label": "ORG", "pattern": "ACM"},
     ]
     ruler.add_patterns(patterns)
-    doc = ruler(nlp.make_doc("Duygu founded her company ACME on her birthday"))
+    doc = nlp("Dina founded her company ACME on her birthday")
     assert len(doc.ents) == 3
     assert doc.ents[0].label_ == "PERSON"
-    assert doc.ents[0].text == "Duygu"
+    assert doc.ents[0].text == "Dina"
     assert doc.ents[1].label_ == "ORG"
     assert doc.ents[1].text == "ACME"
     assert doc.ents[2].label_ == "DATE"
     assert doc.ents[2].text == "her birthday"
-    ruler.remove("duygu")
+    if isinstance(ruler, EntityRuler):
+        ruler.remove("dina")
         ruler.remove("acme")
         ruler.remove("bday")
-    doc = ruler(nlp.make_doc("Duygu went to school"))
+    else:
+        ruler.remove_by_id("dina")
+        ruler.remove_by_id("acme")
+        ruler.remove_by_id("bday")
+    doc = nlp("Dina went to school")
     assert len(doc.ents) == 0
 
 
-def test_entity_ruler_remove_all_patterns(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_remove_all_patterns(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [
-        {"label": "PERSON", "pattern": "Duygu", "id": "duygu"},
+        {"label": "PERSON", "pattern": "Dina", "id": "dina"},
         {"label": "ORG", "pattern": "ACME", "id": "acme"},
         {"label": "DATE", "pattern": "her birthday", "id": "bday"},
     ]
     ruler.add_patterns(patterns)
     assert len(ruler.patterns) == 3
-    ruler.remove("duygu")
+    if isinstance(ruler, EntityRuler):
+        ruler.remove("dina")
+    else:
+        ruler.remove_by_id("dina")
     assert len(ruler.patterns) == 2
+    if isinstance(ruler, EntityRuler):
         ruler.remove("acme")
+    else:
+        ruler.remove_by_id("acme")
     assert len(ruler.patterns) == 1
+    if isinstance(ruler, EntityRuler):
         ruler.remove("bday")
+    else:
+        ruler.remove_by_id("bday")
     assert len(ruler.patterns) == 0
     with pytest.warns(UserWarning):
-        doc = ruler(nlp.make_doc("Duygu founded her company ACME on her birthday"))
+        doc = nlp("Dina founded her company ACME on her birthday")
         assert len(doc.ents) == 0
 
 
-def test_entity_ruler_remove_and_add(nlp):
+@pytest.mark.parametrize("entity_ruler_factory", ENTITY_RULERS)
-    ruler = EntityRuler(nlp)
+def test_entity_ruler_remove_and_add(nlp, entity_ruler_factory):
+    ruler = nlp.add_pipe(entity_ruler_factory, name="entity_ruler")
     patterns = [{"label": "DATE", "pattern": "last time"}]
     ruler.add_patterns(patterns)
     doc = ruler(
@@ -524,7 +608,10 @@ def test_entity_ruler_remove_and_add(nlp):
     assert doc.ents[0].text == "last time"
     assert doc.ents[1].label_ == "DATE"
     assert doc.ents[1].text == "this time"
+    if isinstance(ruler, EntityRuler):
         ruler.remove("ttime")
+    else:
+        ruler.remove_by_id("ttime")
     doc = ruler(
         nlp.make_doc("I saw him last time we met, this time he brought some flowers")
     )
@@ -547,7 +634,10 @@ def test_entity_ruler_remove_and_add(nlp):
     )
     assert len(ruler.patterns) == 3
     assert len(doc.ents) == 3
+    if isinstance(ruler, EntityRuler):
         ruler.remove("ttime")
+    else:
+        ruler.remove_by_id("ttime")
     doc = ruler(
         nlp.make_doc(
             "I saw him last time we met, this time he brought some flowers, another time some chocolate."

spacy/tests/pipeline/test_pipe_factories.py

@@ -119,6 +119,7 @@ def test_pipe_class_component_config():
             self.value1 = value1
             self.value2 = value2
             self.is_base = True
+            self.name = name
 
         def __call__(self, doc: Doc) -> Doc:
             return doc
@@ -141,12 +142,16 @@ def test_pipe_class_component_config():
         nlp.add_pipe(name)
     with pytest.raises(ConfigValidationError):  # invalid config
         nlp.add_pipe(name, config={"value1": "10", "value2": "hello"})
-    nlp.add_pipe(name, config={"value1": 10, "value2": "hello"})
+    with pytest.warns(UserWarning):
+        nlp.add_pipe(
+            name, config={"value1": 10, "value2": "hello", "name": "wrong_name"}
+        )
     pipe = nlp.get_pipe(name)
     assert isinstance(pipe.nlp, Language)
     assert pipe.value1 == 10
     assert pipe.value2 == "hello"
     assert pipe.is_base is True
+    assert pipe.name == name
 
     nlp_en = English()
     with pytest.raises(ConfigValidationError):  # invalid config

spacy/tests/pipeline/test_pipe_methods.py

@@ -4,13 +4,14 @@ import numpy
 import pytest
 from thinc.api import get_current_ops
 
+import spacy
 from spacy.lang.en import English
 from spacy.lang.en.syntax_iterators import noun_chunks
 from spacy.language import Language
 from spacy.pipeline import TrainablePipe
 from spacy.tokens import Doc
 from spacy.training import Example
-from spacy.util import SimpleFrozenList, get_arg_names
+from spacy.util import SimpleFrozenList, get_arg_names, make_tempdir
 from spacy.vocab import Vocab
 
 
@@ -602,3 +603,52 @@ def test_update_with_annotates():
             assert results[component] == "".join(eg.predicted.text for eg in examples)
         for component in components - set(components_to_annotate):
             assert results[component] == ""
+
+
+def test_load_disable_enable() -> None:
+    """
+    Tests spacy.load() with dis-/enabling components.
+    """
+
+    base_nlp = English()
+    for pipe in ("sentencizer", "tagger", "parser"):
+        base_nlp.add_pipe(pipe)
+
+    with make_tempdir() as tmp_dir:
+        base_nlp.to_disk(tmp_dir)
+        to_disable = ["parser", "tagger"]
+        to_enable = ["tagger", "parser"]
+
+        # Setting only `disable`.
+        nlp = spacy.load(tmp_dir, disable=to_disable)
+        assert all([comp_name in nlp.disabled for comp_name in to_disable])
+
+        # Setting only `enable`.
+        nlp = spacy.load(tmp_dir, enable=to_enable)
+        assert all(
+            [
+                (comp_name in nlp.disabled) is (comp_name not in to_enable)
+                for comp_name in nlp.component_names
+            ]
+        )
+
+        # Testing consistent enable/disable combination.
+        nlp = spacy.load(
+            tmp_dir,
+            enable=to_enable,
+            disable=[
+                comp_name
+                for comp_name in nlp.component_names
+                if comp_name not in to_enable
+            ],
+        )
+        assert all(
+            [
+                (comp_name in nlp.disabled) is (comp_name not in to_enable)
+                for comp_name in nlp.component_names
+            ]
+        )
+
+        # Inconsistent enable/disable combination.
+        with pytest.raises(ValueError):
+            spacy.load(tmp_dir, enable=to_enable, disable=["parser"])

spacy/tests/pipeline/test_span_ruler.py

@@ -0,0 +1,465 @@
+import pytest
+
+import spacy
+from spacy import registry
+from spacy.errors import MatchPatternError
+from spacy.tokens import Span
+from spacy.training import Example
+from spacy.tests.util import make_tempdir
+
+from thinc.api import NumpyOps, get_current_ops
+
+
+@pytest.fixture
+@registry.misc("span_ruler_patterns")
+def patterns():
+    return [
+        {"label": "HELLO", "pattern": "hello world", "id": "hello1"},
+        {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
+        {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}], "id": "hello2"},
+        {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
+        {"label": "TECH_ORG", "pattern": "Apple"},
+        {"label": "TECH_ORG", "pattern": "Microsoft"},
+    ]
+
+
+@pytest.fixture
+def overlapping_patterns():
+    return [
+        {"label": "FOOBAR", "pattern": "foo bar"},
+        {"label": "BARBAZ", "pattern": "bar baz"},
+    ]
+
+
+@pytest.fixture
+def person_org_patterns():
+    return [
+        {"label": "PERSON", "pattern": "Dina"},
+        {"label": "ORG", "pattern": "ACME"},
+        {"label": "ORG", "pattern": "ACM"},
+    ]
+
+
+@pytest.fixture
+def person_org_date_patterns(person_org_patterns):
+    return person_org_patterns + [{"label": "DATE", "pattern": "June 14th"}]
+
+
+def test_span_ruler_add_empty(patterns):
+    """Test that patterns don't get added excessively."""
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler", config={"validate": True})
+    ruler.add_patterns(patterns)
+    pattern_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
+    assert pattern_count > 0
+    ruler.add_patterns([])
+    after_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
+    assert after_count == pattern_count
+
+
+def test_span_ruler_init(patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(patterns)
+    assert len(ruler) == len(patterns)
+    assert len(ruler.labels) == 4
+    assert "HELLO" in ruler
+    assert "BYE" in ruler
+    doc = nlp("hello world bye bye")
+    assert len(doc.spans["ruler"]) == 2
+    assert doc.spans["ruler"][0].label_ == "HELLO"
+    assert doc.spans["ruler"][0].id_ == "hello1"
+    assert doc.spans["ruler"][1].label_ == "BYE"
+    assert doc.spans["ruler"][1].id_ == ""
+
+
+def test_span_ruler_no_patterns_warns():
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    assert len(ruler) == 0
+    assert len(ruler.labels) == 0
+    assert nlp.pipe_names == ["span_ruler"]
+    with pytest.warns(UserWarning):
+        doc = nlp("hello world bye bye")
+    assert len(doc.spans["ruler"]) == 0
+
+
+def test_span_ruler_init_patterns(patterns):
+    # initialize with patterns
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    assert len(ruler.labels) == 0
+    ruler.initialize(lambda: [], patterns=patterns)
+    assert len(ruler.labels) == 4
+    doc = nlp("hello world bye bye")
+    assert doc.spans["ruler"][0].label_ == "HELLO"
+    assert doc.spans["ruler"][1].label_ == "BYE"
+    nlp.remove_pipe("span_ruler")
+    # initialize with patterns from misc registry
+    nlp.config["initialize"]["components"]["span_ruler"] = {
+        "patterns": {"@misc": "span_ruler_patterns"}
+    }
+    ruler = nlp.add_pipe("span_ruler")
+    assert len(ruler.labels) == 0
+    nlp.initialize()
+    assert len(ruler.labels) == 4
+    doc = nlp("hello world bye bye")
+    assert doc.spans["ruler"][0].label_ == "HELLO"
+    assert doc.spans["ruler"][1].label_ == "BYE"
+
+
+def test_span_ruler_init_clear(patterns):
+    """Test that initialization clears patterns."""
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(patterns)
+    assert len(ruler.labels) == 4
+    ruler.initialize(lambda: [])
+    assert len(ruler.labels) == 0
+
+
+def test_span_ruler_clear(patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(patterns)
+    assert len(ruler.labels) == 4
+    doc = nlp("hello world")
+    assert len(doc.spans["ruler"]) == 1
+    ruler.clear()
+    assert len(ruler.labels) == 0
+    with pytest.warns(UserWarning):
+        doc = nlp("hello world")
+    assert len(doc.spans["ruler"]) == 0
+
+
+def test_span_ruler_existing(patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler", config={"overwrite": False})
+    ruler.add_patterns(patterns)
+    doc = nlp.make_doc("OH HELLO WORLD bye bye")
+    doc.spans["ruler"] = [doc[0:2]]
+    doc = nlp(doc)
+    assert len(doc.spans["ruler"]) == 3
+    assert doc.spans["ruler"][0] == doc[0:2]
+    assert doc.spans["ruler"][1].label_ == "HELLO"
+    assert doc.spans["ruler"][1].id_ == "hello2"
+    assert doc.spans["ruler"][2].label_ == "BYE"
+    assert doc.spans["ruler"][2].id_ == ""
+
+
+def test_span_ruler_existing_overwrite(patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler", config={"overwrite": True})
+    ruler.add_patterns(patterns)
+    doc = nlp.make_doc("OH HELLO WORLD bye bye")
+    doc.spans["ruler"] = [doc[0:2]]
+    doc = nlp(doc)
+    assert len(doc.spans["ruler"]) == 2
+    assert doc.spans["ruler"][0].label_ == "HELLO"
+    assert doc.spans["ruler"][0].text == "HELLO"
+    assert doc.spans["ruler"][1].label_ == "BYE"
+
+
+def test_span_ruler_serialize_bytes(patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(patterns)
+    assert len(ruler) == len(patterns)
+    assert len(ruler.labels) == 4
+    ruler_bytes = ruler.to_bytes()
+    new_nlp = spacy.blank("xx")
+    new_ruler = new_nlp.add_pipe("span_ruler")
+    assert len(new_ruler) == 0
+    assert len(new_ruler.labels) == 0
+    new_ruler = new_ruler.from_bytes(ruler_bytes)
+    assert len(new_ruler) == len(patterns)
+    assert len(new_ruler.labels) == 4
+    assert len(new_ruler.patterns) == len(ruler.patterns)
+    for pattern in ruler.patterns:
+        assert pattern in new_ruler.patterns
+    assert sorted(new_ruler.labels) == sorted(ruler.labels)
+
+
+def test_span_ruler_validate():
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    validated_ruler = nlp.add_pipe(
+        "span_ruler", name="validated_span_ruler", config={"validate": True}
+    )
+
+    valid_pattern = {"label": "HELLO", "pattern": [{"LOWER": "HELLO"}]}
+    invalid_pattern = {"label": "HELLO", "pattern": [{"ASDF": "HELLO"}]}
+
+    # invalid pattern raises error without validate
+    with pytest.raises(ValueError):
+        ruler.add_patterns([invalid_pattern])
+
+    # valid pattern is added without errors with validate
+    validated_ruler.add_patterns([valid_pattern])
+
+    # invalid pattern raises error with validate
+    with pytest.raises(MatchPatternError):
+        validated_ruler.add_patterns([invalid_pattern])
+
+
+def test_span_ruler_properties(patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler", config={"overwrite": True})
+    ruler.add_patterns(patterns)
+    assert sorted(ruler.labels) == sorted(set([p["label"] for p in patterns]))
+
+
+def test_span_ruler_overlapping_spans(overlapping_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(overlapping_patterns)
+    doc = ruler(nlp.make_doc("foo bar baz"))
+    assert len(doc.spans["ruler"]) == 2
+    assert doc.spans["ruler"][0].label_ == "FOOBAR"
+    assert doc.spans["ruler"][1].label_ == "BARBAZ"
+
+
+def test_span_ruler_scorer(overlapping_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(overlapping_patterns)
+    text = "foo bar baz"
+    pred_doc = ruler(nlp.make_doc(text))
+    assert len(pred_doc.spans["ruler"]) == 2
+    assert pred_doc.spans["ruler"][0].label_ == "FOOBAR"
+    assert pred_doc.spans["ruler"][1].label_ == "BARBAZ"
+
+    ref_doc = nlp.make_doc(text)
+    ref_doc.spans["ruler"] = [Span(ref_doc, 0, 2, label="FOOBAR")]
+    scores = nlp.evaluate([Example(pred_doc, ref_doc)])
+    assert scores["spans_ruler_p"] == 0.5
+    assert scores["spans_ruler_r"] == 1.0
+
+
+@pytest.mark.parametrize("n_process", [1, 2])
+def test_span_ruler_multiprocessing(n_process):
+    if isinstance(get_current_ops, NumpyOps) or n_process < 2:
+        texts = ["I enjoy eating Pizza Hut pizza."]
+
+        patterns = [{"label": "FASTFOOD", "pattern": "Pizza Hut"}]
+
+        nlp = spacy.blank("xx")
+        ruler = nlp.add_pipe("span_ruler")
+        ruler.add_patterns(patterns)
+
+        for doc in nlp.pipe(texts, n_process=2):
+            for ent in doc.spans["ruler"]:
+                assert ent.label_ == "FASTFOOD"
+
+
+def test_span_ruler_serialize_dir(patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(patterns)
+    with make_tempdir() as d:
+        ruler.to_disk(d / "test_ruler")
+        ruler.from_disk(d / "test_ruler")  # read from an existing directory
+        with pytest.raises(ValueError):
+            ruler.from_disk(d / "non_existing_dir")  # read from a bad directory
+
+
+def test_span_ruler_remove_basic(person_org_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(person_org_patterns)
+    doc = ruler(nlp.make_doc("Dina went to school"))
+    assert len(ruler.patterns) == 3
+    assert len(doc.spans["ruler"]) == 1
+    assert doc.spans["ruler"][0].label_ == "PERSON"
+    assert doc.spans["ruler"][0].text == "Dina"
+    ruler.remove("PERSON")
+    doc = ruler(nlp.make_doc("Dina went to school"))
+    assert len(doc.spans["ruler"]) == 0
+    assert len(ruler.patterns) == 2
+
+
+def test_span_ruler_remove_nonexisting_pattern(person_org_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(person_org_patterns)
+    assert len(ruler.patterns) == 3
+    with pytest.raises(ValueError):
+        ruler.remove("NE")
+    with pytest.raises(ValueError):
+        ruler.remove_by_id("NE")
+
+
+def test_span_ruler_remove_several_patterns(person_org_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(person_org_patterns)
+    doc = ruler(nlp.make_doc("Dina founded the company ACME."))
+    assert len(ruler.patterns) == 3
+    assert len(doc.spans["ruler"]) == 2
+    assert doc.spans["ruler"][0].label_ == "PERSON"
+    assert doc.spans["ruler"][0].text == "Dina"
+    assert doc.spans["ruler"][1].label_ == "ORG"
+    assert doc.spans["ruler"][1].text == "ACME"
+    ruler.remove("PERSON")
+    doc = ruler(nlp.make_doc("Dina founded the company ACME"))
+    assert len(ruler.patterns) == 2
+    assert len(doc.spans["ruler"]) == 1
+    assert doc.spans["ruler"][0].label_ == "ORG"
+    assert doc.spans["ruler"][0].text == "ACME"
+    ruler.remove("ORG")
+    with pytest.warns(UserWarning):
+        doc = ruler(nlp.make_doc("Dina founded the company ACME"))
+        assert len(ruler.patterns) == 0
+        assert len(doc.spans["ruler"]) == 0
+
+
+def test_span_ruler_remove_patterns_in_a_row(person_org_date_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(person_org_date_patterns)
+    doc = ruler(nlp.make_doc("Dina founded the company ACME on June 14th"))
+    assert len(doc.spans["ruler"]) == 3
+    assert doc.spans["ruler"][0].label_ == "PERSON"
+    assert doc.spans["ruler"][0].text == "Dina"
+    assert doc.spans["ruler"][1].label_ == "ORG"
+    assert doc.spans["ruler"][1].text == "ACME"
+    assert doc.spans["ruler"][2].label_ == "DATE"
+    assert doc.spans["ruler"][2].text == "June 14th"
+    ruler.remove("ORG")
+    ruler.remove("DATE")
+    doc = ruler(nlp.make_doc("Dina went to school"))
+    assert len(doc.spans["ruler"]) == 1
+
+
+def test_span_ruler_remove_all_patterns(person_org_date_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    ruler.add_patterns(person_org_date_patterns)
+    assert len(ruler.patterns) == 4
+    ruler.remove("PERSON")
+    assert len(ruler.patterns) == 3
+    ruler.remove("ORG")
+    assert len(ruler.patterns) == 1
+    ruler.remove("DATE")
+    assert len(ruler.patterns) == 0
+    with pytest.warns(UserWarning):
+        doc = ruler(nlp.make_doc("Dina founded the company ACME on June 14th"))
+        assert len(doc.spans["ruler"]) == 0
+
+
+def test_span_ruler_remove_and_add():
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler")
+    patterns1 = [{"label": "DATE1", "pattern": "last time"}]
+    ruler.add_patterns(patterns1)
+    doc = ruler(
+        nlp.make_doc("I saw him last time we met, this time he brought some flowers")
+    )
+    assert len(ruler.patterns) == 1
+    assert len(doc.spans["ruler"]) == 1
+    assert doc.spans["ruler"][0].label_ == "DATE1"
+    assert doc.spans["ruler"][0].text == "last time"
+    patterns2 = [{"label": "DATE2", "pattern": "this time"}]
+    ruler.add_patterns(patterns2)
+    doc = ruler(
+        nlp.make_doc("I saw him last time we met, this time he brought some flowers")
+    )
+    assert len(ruler.patterns) == 2
+    assert len(doc.spans["ruler"]) == 2
+    assert doc.spans["ruler"][0].label_ == "DATE1"
+    assert doc.spans["ruler"][0].text == "last time"
+    assert doc.spans["ruler"][1].label_ == "DATE2"
+    assert doc.spans["ruler"][1].text == "this time"
+    ruler.remove("DATE1")
+    doc = ruler(
+        nlp.make_doc("I saw him last time we met, this time he brought some flowers")
+    )
+    assert len(ruler.patterns) == 1
+    assert len(doc.spans["ruler"]) == 1
+    assert doc.spans["ruler"][0].label_ == "DATE2"
+    assert doc.spans["ruler"][0].text == "this time"
+    ruler.add_patterns(patterns1)
+    doc = ruler(
+        nlp.make_doc("I saw him last time we met, this time he brought some flowers")
+    )
+    assert len(ruler.patterns) == 2
+    assert len(doc.spans["ruler"]) == 2
+    patterns3 = [{"label": "DATE3", "pattern": "another time"}]
+    ruler.add_patterns(patterns3)
+    doc = ruler(
+        nlp.make_doc(
+            "I saw him last time we met, this time he brought some flowers, another time some chocolate."
+        )
+    )
+    assert len(ruler.patterns) == 3
+    assert len(doc.spans["ruler"]) == 3
+    ruler.remove("DATE3")
+    doc = ruler(
+        nlp.make_doc(
+            "I saw him last time we met, this time he brought some flowers, another time some chocolate."
+        )
+    )
+    assert len(ruler.patterns) == 2
+    assert len(doc.spans["ruler"]) == 2
+
+
+def test_span_ruler_spans_filter(overlapping_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe(
+        "span_ruler",
+        config={"spans_filter": {"@misc": "spacy.first_longest_spans_filter.v1"}},
+    )
+    ruler.add_patterns(overlapping_patterns)
+    doc = ruler(nlp.make_doc("foo bar baz"))
+    assert len(doc.spans["ruler"]) == 1
+    assert doc.spans["ruler"][0].label_ == "FOOBAR"
+
+
+def test_span_ruler_ents_default_filter(overlapping_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe("span_ruler", config={"annotate_ents": True})
+    ruler.add_patterns(overlapping_patterns)
+    doc = ruler(nlp.make_doc("foo bar baz"))
+    assert len(doc.ents) == 1
+    assert doc.ents[0].label_ == "FOOBAR"
+
+
+def test_span_ruler_ents_overwrite_filter(overlapping_patterns):
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe(
+        "span_ruler",
+        config={
+            "annotate_ents": True,
+            "overwrite": False,
+            "ents_filter": {"@misc": "spacy.prioritize_new_ents_filter.v1"},
+        },
+    )
+    ruler.add_patterns(overlapping_patterns)
+    # overlapping ents are clobbered, non-overlapping ents are preserved
+    doc = nlp.make_doc("foo bar baz a b c")
+    doc.ents = [Span(doc, 1, 3, label="BARBAZ"), Span(doc, 3, 6, label="ABC")]
+    doc = ruler(doc)
+    assert len(doc.ents) == 2
+    assert doc.ents[0].label_ == "FOOBAR"
+    assert doc.ents[1].label_ == "ABC"
+
+
+def test_span_ruler_ents_bad_filter(overlapping_patterns):
+    @registry.misc("test_pass_through_filter")
+    def make_pass_through_filter():
+        def pass_through_filter(spans1, spans2):
+            return spans1 + spans2
+
+        return pass_through_filter
+
+    nlp = spacy.blank("xx")
+    ruler = nlp.add_pipe(
+        "span_ruler",
+        config={
+            "annotate_ents": True,
+            "ents_filter": {"@misc": "test_pass_through_filter"},
+        },
+    )
+    ruler.add_patterns(overlapping_patterns)
+    with pytest.raises(ValueError):
+        ruler(nlp.make_doc("foo bar baz"))

spacy/tests/pipeline/test_textcat.py

@@ -382,6 +382,7 @@ def test_implicit_label(name, get_examples):
 
 
 # fmt: off
+@pytest.mark.slow
 @pytest.mark.parametrize(
     "name,textcat_config",
     [
@@ -390,7 +391,10 @@ def test_implicit_label(name, get_examples):
         ("textcat", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
         ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
         ("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
-        # ENSEMBLE
+        # ENSEMBLE V1
+        ("textcat", {"@architectures": "spacy.TextCatEnsemble.v1", "exclusive_classes": False, "pretrained_vectors": None, "width": 64, "embed_size": 2000, "conv_depth": 2, "window_size": 1, "ngram_size": 1, "dropout": None}),
+        ("textcat_multilabel", {"@architectures": "spacy.TextCatEnsemble.v1", "exclusive_classes": False, "pretrained_vectors": None, "width": 64, "embed_size": 2000, "conv_depth": 2, "window_size": 1, "ngram_size": 1, "dropout": None}),
+        # ENSEMBLE V2
         ("textcat", {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": True, "no_output_layer": False, "ngram_size": 3}}),
         ("textcat", {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}}),
         ("textcat_multilabel", {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}}),
@@ -643,15 +647,28 @@ def test_overfitting_IO_multi():
 
 
 # fmt: off
+@pytest.mark.slow
 @pytest.mark.parametrize(
     "name,train_data,textcat_config",
     [
+        # BOW V1
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}),
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v1", "exclusive_classes": True, "ngram_size": 4, "no_output_layer": False}),
+        # ENSEMBLE V1
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatEnsemble.v1", "exclusive_classes": False, "pretrained_vectors": None, "width": 64, "embed_size": 2000, "conv_depth": 2, "window_size": 1, "ngram_size": 1, "dropout": None}),
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatEnsemble.v1", "exclusive_classes": False, "pretrained_vectors": None, "width": 64, "embed_size": 2000, "conv_depth": 2, "window_size": 1, "ngram_size": 1, "dropout": None}),
+        # CNN V1
+        ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatCNN.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
+        ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatCNN.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
+        # BOW V2
         ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}),
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 4, "no_output_layer": False}),
         ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "ngram_size": 3, "no_output_layer": True}),
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 2, "no_output_layer": True}),
+        # ENSEMBLE V2
         ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}}),
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v2", "exclusive_classes": True, "ngram_size": 5, "no_output_layer": False}}),
+        # CNN V2
         ("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
         ("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
     ],

spacy/tests/pipeline/test_tok2vec.py

@@ -1,13 +1,13 @@
 import pytest
 from spacy.ml.models.tok2vec import build_Tok2Vec_model
-from spacy.ml.models.tok2vec import MultiHashEmbed, CharacterEmbed
+from spacy.ml.models.tok2vec import MultiHashEmbed, MaxoutWindowEncoder
-from spacy.ml.models.tok2vec import MishWindowEncoder, MaxoutWindowEncoder
 from spacy.pipeline.tok2vec import Tok2Vec, Tok2VecListener
 from spacy.vocab import Vocab
 from spacy.tokens import Doc
 from spacy.training import Example
 from spacy import util
 from spacy.lang.en import English
+from spacy.util import registry
 from thinc.api import Config, get_current_ops
 from numpy.testing import assert_array_equal
 
@@ -55,24 +55,41 @@ def test_tok2vec_batch_sizes(batch_size, width, embed_size):
         assert doc_vec.shape == (len(doc), width)
 
 
+@pytest.mark.slow
+@pytest.mark.parametrize("width", [8])
 @pytest.mark.parametrize(
-    "width,embed_arch,embed_config,encode_arch,encode_config",
+    "embed_arch,embed_config",
     # fmt: off
     [
-        (8, MultiHashEmbed, {"rows": [100, 100], "attrs": ["SHAPE", "LOWER"], "include_static_vectors": False}, MaxoutWindowEncoder, {"window_size": 1, "maxout_pieces": 3, "depth": 2}),
+        ("spacy.MultiHashEmbed.v1", {"rows": [100, 100], "attrs": ["SHAPE", "LOWER"], "include_static_vectors": False}),
-        (8, MultiHashEmbed, {"rows": [100, 20], "attrs": ["ORTH", "PREFIX"], "include_static_vectors": False}, MishWindowEncoder, {"window_size": 1, "depth": 6}),
+        ("spacy.MultiHashEmbed.v1", {"rows": [100, 20], "attrs": ["ORTH", "PREFIX"], "include_static_vectors": False}),
-        (8, CharacterEmbed, {"rows": 100, "nM": 64, "nC": 8, "include_static_vectors": False}, MaxoutWindowEncoder, {"window_size": 1, "maxout_pieces": 3, "depth": 3}),
+        ("spacy.CharacterEmbed.v1", {"rows": 100, "nM": 64, "nC": 8, "include_static_vectors": False}),
-        (8, CharacterEmbed, {"rows": 100, "nM": 16, "nC": 2, "include_static_vectors": False}, MishWindowEncoder, {"window_size": 1, "depth": 3}),
+        ("spacy.CharacterEmbed.v1", {"rows": 100, "nM": 16, "nC": 2, "include_static_vectors": False}),
     ],
     # fmt: on
 )
-def test_tok2vec_configs(width, embed_arch, embed_config, encode_arch, encode_config):
+@pytest.mark.parametrize(
+    "tok2vec_arch,encode_arch,encode_config",
+    # fmt: off
+    [
+        ("spacy.Tok2Vec.v1", "spacy.MaxoutWindowEncoder.v1", {"window_size": 1, "maxout_pieces": 3, "depth": 2}),
+        ("spacy.Tok2Vec.v2", "spacy.MaxoutWindowEncoder.v2", {"window_size": 1, "maxout_pieces": 3, "depth": 2}),
+        ("spacy.Tok2Vec.v1", "spacy.MishWindowEncoder.v1", {"window_size": 1, "depth": 6}),
+        ("spacy.Tok2Vec.v2", "spacy.MishWindowEncoder.v2", {"window_size": 1, "depth": 6}),
+    ],
+    # fmt: on
+)
+def test_tok2vec_configs(
+    width, tok2vec_arch, embed_arch, embed_config, encode_arch, encode_config
+):
+    embed = registry.get("architectures", embed_arch)
+    encode = registry.get("architectures", encode_arch)
+    tok2vec_model = registry.get("architectures", tok2vec_arch)
+
     embed_config["width"] = width
     encode_config["width"] = width
     docs = get_batch(3)
-    tok2vec = build_Tok2Vec_model(
+    tok2vec = tok2vec_model(embed(**embed_config), encode(**encode_config))
-        embed_arch(**embed_config), encode_arch(**encode_config)
-    )
     tok2vec.initialize(docs)
     vectors, backprop = tok2vec.begin_update(docs)
     assert len(vectors) == len(docs)

spacy/tests/serialize/test_serialize_span_groups.py

@@ -0,0 +1,161 @@
+import pytest
+
+from spacy.tokens import Span, SpanGroup
+from spacy.tokens._dict_proxies import SpanGroups
+
+
+@pytest.mark.issue(10685)
+def test_issue10685(en_tokenizer):
+    """Test `SpanGroups` de/serialization"""
+    # Start with a Doc with no SpanGroups
+    doc = en_tokenizer("Will it blend?")
+
+    # Test empty `SpanGroups` de/serialization:
+    assert len(doc.spans) == 0
+    doc.spans.from_bytes(doc.spans.to_bytes())
+    assert len(doc.spans) == 0
+
+    # Test non-empty `SpanGroups` de/serialization:
+    doc.spans["test"] = SpanGroup(doc, name="test", spans=[doc[0:1]])
+    doc.spans["test2"] = SpanGroup(doc, name="test", spans=[doc[1:2]])
+
+    def assert_spangroups():
+        assert len(doc.spans) == 2
+        assert doc.spans["test"].name == "test"
+        assert doc.spans["test2"].name == "test"
+        assert list(doc.spans["test"]) == [doc[0:1]]
+        assert list(doc.spans["test2"]) == [doc[1:2]]
+
+    # Sanity check the currently-expected behavior
+    assert_spangroups()
+
+    # Now test serialization/deserialization:
+    doc.spans.from_bytes(doc.spans.to_bytes())
+
+    assert_spangroups()
+
+
+def test_span_groups_serialization_mismatches(en_tokenizer):
+    """Test the serialization of multiple mismatching `SpanGroups` keys and `SpanGroup.name`s"""
+    doc = en_tokenizer("How now, brown cow?")
+    # Some variety:
+    # 1 SpanGroup where its name matches its key
+    # 2 SpanGroups that have the same name--which is not a key
+    # 2 SpanGroups that have the same name--which is a key
+    # 1 SpanGroup that is a value for 2 different keys (where its name is a key)
+    # 1 SpanGroup that is a value for 2 different keys (where its name is not a key)
+    groups = doc.spans
+    groups["key1"] = SpanGroup(doc, name="key1", spans=[doc[0:1], doc[1:2]])
+    groups["key2"] = SpanGroup(doc, name="too", spans=[doc[3:4], doc[4:5]])
+    groups["key3"] = SpanGroup(doc, name="too", spans=[doc[1:2], doc[0:1]])
+    groups["key4"] = SpanGroup(doc, name="key4", spans=[doc[0:1]])
+    groups["key5"] = SpanGroup(doc, name="key4", spans=[doc[0:1]])
+    sg6 = SpanGroup(doc, name="key6", spans=[doc[0:1]])
+    groups["key6"] = sg6
+    groups["key7"] = sg6
+    sg8 = SpanGroup(doc, name="also", spans=[doc[1:2]])
+    groups["key8"] = sg8
+    groups["key9"] = sg8
+
+    regroups = SpanGroups(doc).from_bytes(groups.to_bytes())
+
+    # Assert regroups == groups
+    assert regroups.keys() == groups.keys()
+    for key, regroup in regroups.items():
+        # Assert regroup == groups[key]
+        assert regroup.name == groups[key].name
+        assert list(regroup) == list(groups[key])
+
+
+@pytest.mark.parametrize(
+    "spans_bytes,doc_text,expected_spangroups,expected_warning",
+    # The bytestrings below were generated from an earlier version of spaCy
+    # that serialized `SpanGroups` as a list of SpanGroup bytes (via SpanGroups.to_bytes).
+    # Comments preceding the bytestrings indicate from what Doc they were created.
+    [
+        # Empty SpanGroups:
+        (b"\x90", "", {}, False),
+        # doc = nlp("Will it blend?")
+        # doc.spans['test'] = SpanGroup(doc, name='test', spans=[doc[0:1]])
+        (
+            b"\x91\xc4C\x83\xa4name\xa4test\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x04",
+            "Will it blend?",
+            {"test": {"name": "test", "spans": [(0, 1)]}},
+            False,
+        ),
+        # doc = nlp("Will it blend?")
+        # doc.spans['test']  = SpanGroup(doc, name='test', spans=[doc[0:1]])
+        # doc.spans['test2'] = SpanGroup(doc, name='test', spans=[doc[1:2]])
+        (
+            b"\x92\xc4C\x83\xa4name\xa4test\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x04\xc4C\x83\xa4name\xa4test\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x02\x00\x00\x00\x05\x00\x00\x00\x07",
+            "Will it blend?",
+            # We expect only 1 SpanGroup to be in doc.spans in this example
+            # because there are 2 `SpanGroup`s that have the same .name. See #10685.
+            {"test": {"name": "test", "spans": [(1, 2)]}},
+            True,
+        ),
+        # doc = nlp('How now, brown cow?')
+        # doc.spans['key1'] = SpanGroup(doc, name='key1', spans=[doc[0:1], doc[1:2]])
+        # doc.spans['key2'] = SpanGroup(doc, name='too', spans=[doc[3:4], doc[4:5]])
+        # doc.spans['key3'] = SpanGroup(doc, name='too', spans=[doc[1:2], doc[0:1]])
+        # doc.spans['key4'] = SpanGroup(doc, name='key4', spans=[doc[0:1]])
+        # doc.spans['key5'] = SpanGroup(doc, name='key4', spans=[doc[0:1]])
+        (
+            b"\x95\xc4m\x83\xa4name\xa4key1\xa5attrs\x80\xa5spans\x92\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x03\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x02\x00\x00\x00\x04\x00\x00\x00\x07\xc4l\x83\xa4name\xa3too\xa5attrs\x80\xa5spans\x92\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x03\x00\x00\x00\x04\x00\x00\x00\t\x00\x00\x00\x0e\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x05\x00\x00\x00\x0f\x00\x00\x00\x12\xc4l\x83\xa4name\xa3too\xa5attrs\x80\xa5spans\x92\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x02\x00\x00\x00\x04\x00\x00\x00\x07\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x03\xc4C\x83\xa4name\xa4key4\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x03\xc4C\x83\xa4name\xa4key4\xa5attrs\x80\xa5spans\x91\xc4(\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x03",
+            "How now, brown cow?",
+            {
+                "key1": {"name": "key1", "spans": [(0, 1), (1, 2)]},
+                "too": {"name": "too", "spans": [(1, 2), (0, 1)]},
+                "key4": {"name": "key4", "spans": [(0, 1)]},
+            },
+            True,
+        ),
+    ],
+)
+def test_deserialize_span_groups_compat(
+    en_tokenizer, spans_bytes, doc_text, expected_spangroups, expected_warning
+):
+    """Test backwards-compatibility of `SpanGroups` deserialization.
+    This uses serializations (bytes) from a prior version of spaCy (before 3.3.1).
+
+    spans_bytes (bytes): Serialized `SpanGroups` object.
+    doc_text (str): Doc text.
+    expected_spangroups (dict):
+        Dict mapping every expected (after deserialization) `SpanGroups` key
+        to a SpanGroup's "args", where a SpanGroup's args are given as a dict:
+          {"name": span_group.name,
+           "spans": [(span0.start, span0.end), ...]}
+    expected_warning (bool): Whether a warning is to be expected from .from_bytes()
+        --i.e. if more than 1 SpanGroup has the same .name within the `SpanGroups`.
+    """
+    doc = en_tokenizer(doc_text)
+
+    if expected_warning:
+        with pytest.warns(UserWarning):
+            doc.spans.from_bytes(spans_bytes)
+    else:
+        # TODO: explicitly check for lack of a warning
+        doc.spans.from_bytes(spans_bytes)
+
+    assert doc.spans.keys() == expected_spangroups.keys()
+    for name, spangroup_args in expected_spangroups.items():
+        assert doc.spans[name].name == spangroup_args["name"]
+        spans = [Span(doc, start, end) for start, end in spangroup_args["spans"]]
+        assert list(doc.spans[name]) == spans
+
+
+def test_span_groups_serialization(en_tokenizer):
+    doc = en_tokenizer("0 1 2 3 4 5 6")
+    span_groups = SpanGroups(doc)
+    spans = [doc[0:2], doc[1:3]]
+    sg1 = SpanGroup(doc, spans=spans)
+    span_groups["key1"] = sg1
+    span_groups["key2"] = sg1
+    span_groups["key3"] = []
+    reloaded_span_groups = SpanGroups(doc).from_bytes(span_groups.to_bytes())
+    assert span_groups.keys() == reloaded_span_groups.keys()
+    for key, value in span_groups.items():
+        assert all(
+            span == reloaded_span
+            for span, reloaded_span in zip(span_groups[key], reloaded_span_groups[key])
+        )

spacy/tests/test_cli.py

@@ -1,4 +1,7 @@
 import os
+import math
+from random import sample
+from typing import Counter
 
 import pytest
 import srsly
@@ -14,6 +17,10 @@ from spacy.cli._util import substitute_project_variables
 from spacy.cli._util import validate_project_commands
 from spacy.cli.debug_data import _compile_gold, _get_labels_from_model
 from spacy.cli.debug_data import _get_labels_from_spancat
+from spacy.cli.debug_data import _get_distribution, _get_kl_divergence
+from spacy.cli.debug_data import _get_span_characteristics
+from spacy.cli.debug_data import _print_span_characteristics
+from spacy.cli.debug_data import _get_spans_length_freq_dist
 from spacy.cli.download import get_compatibility, get_version
 from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config
 from spacy.cli.package import get_third_party_dependencies
@@ -24,6 +31,7 @@ from spacy.lang.nl import Dutch
 from spacy.language import Language
 from spacy.schemas import ProjectConfigSchema, RecommendationSchema, validate
 from spacy.tokens import Doc
+from spacy.tokens.span import Span
 from spacy.training import Example, docs_to_json, offsets_to_biluo_tags
 from spacy.training.converters import conll_ner_to_docs, conllu_to_docs
 from spacy.training.converters import iob_to_docs
@@ -341,6 +349,7 @@ def test_project_config_validation_full():
         "assets": [
             {
                 "dest": "x",
+                "extra": True,
                 "url": "https://example.com",
                 "checksum": "63373dd656daa1fd3043ce166a59474c",
             },
@@ -352,6 +361,12 @@ def test_project_config_validation_full():
                     "path": "y",
                 },
             },
+            {
+                "dest": "z",
+                "extra": False,
+                "url": "https://example.com",
+                "checksum": "63373dd656daa1fd3043ce166a59474c",
+            },
         ],
         "commands": [
             {
@@ -733,3 +748,110 @@ def test_debug_data_compile_gold():
     eg = Example(pred, ref)
     data = _compile_gold([eg], ["ner"], nlp, True)
     assert data["boundary_cross_ents"] == 1
+
+
+def test_debug_data_compile_gold_for_spans():
+    nlp = English()
+    spans_key = "sc"
+
+    pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
+    pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
+    ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
+    ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
+    eg = Example(pred, ref)
+
+    data = _compile_gold([eg], ["spancat"], nlp, True)
+
+    assert data["spancat"][spans_key] == Counter({"ORG": 1, "GPE": 1})
+    assert data["spans_length"][spans_key] == {"ORG": [3], "GPE": [1]}
+    assert data["spans_per_type"][spans_key] == {
+        "ORG": [Span(ref, 3, 6, "ORG")],
+        "GPE": [Span(ref, 5, 6, "GPE")],
+    }
+    assert data["sb_per_type"][spans_key] == {
+        "ORG": {"start": [ref[2:3]], "end": [ref[6:7]]},
+        "GPE": {"start": [ref[4:5]], "end": [ref[6:7]]},
+    }
+
+
+def test_frequency_distribution_is_correct():
+    nlp = English()
+    docs = [
+        Doc(nlp.vocab, words=["Bank", "of", "China"]),
+        Doc(nlp.vocab, words=["China"]),
+    ]
+
+    expected = Counter({"china": 0.5, "bank": 0.25, "of": 0.25})
+    freq_distribution = _get_distribution(docs, normalize=True)
+    assert freq_distribution == expected
+
+
+def test_kl_divergence_computation_is_correct():
+    p = Counter({"a": 0.5, "b": 0.25})
+    q = Counter({"a": 0.25, "b": 0.50, "c": 0.15, "d": 0.10})
+    result = _get_kl_divergence(p, q)
+    expected = 0.1733
+    assert math.isclose(result, expected, rel_tol=1e-3)
+
+
+def test_get_span_characteristics_return_value():
+    nlp = English()
+    spans_key = "sc"
+
+    pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
+    pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
+    ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
+    ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
+    eg = Example(pred, ref)
+
+    examples = [eg]
+    data = _compile_gold(examples, ["spancat"], nlp, True)
+    span_characteristics = _get_span_characteristics(
+        examples=examples, compiled_gold=data, spans_key=spans_key
+    )
+
+    assert {"sd", "bd", "lengths"}.issubset(span_characteristics.keys())
+    assert span_characteristics["min_length"] == 1
+    assert span_characteristics["max_length"] == 3
+
+
+def test_ensure_print_span_characteristics_wont_fail():
+    """Test if interface between two methods aren't destroyed if refactored"""
+    nlp = English()
+    spans_key = "sc"
+
+    pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
+    pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
+    ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
+    ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
+    eg = Example(pred, ref)
+
+    examples = [eg]
+    data = _compile_gold(examples, ["spancat"], nlp, True)
+    span_characteristics = _get_span_characteristics(
+        examples=examples, compiled_gold=data, spans_key=spans_key
+    )
+    _print_span_characteristics(span_characteristics)
+
+
+@pytest.mark.parametrize("threshold", [70, 80, 85, 90, 95])
+def test_span_length_freq_dist_threshold_must_be_correct(threshold):
+    sample_span_lengths = {
+        "span_type_1": [1, 4, 4, 5],
+        "span_type_2": [5, 3, 3, 2],
+        "span_type_3": [3, 1, 3, 3],
+    }
+    span_freqs = _get_spans_length_freq_dist(sample_span_lengths, threshold)
+    assert sum(span_freqs.values()) >= threshold
+
+
+def test_span_length_freq_dist_output_must_be_correct():
+    sample_span_lengths = {
+        "span_type_1": [1, 4, 4, 5],
+        "span_type_2": [5, 3, 3, 2],
+        "span_type_3": [3, 1, 3, 3],
+    }
+    threshold = 90
+    span_freqs = _get_spans_length_freq_dist(sample_span_lengths, threshold)
+    assert sum(span_freqs.values()) >= threshold
+    assert list(span_freqs.keys()) == [3, 1, 4, 5, 2]

spacy/tests/tokenizer/test_explain.py

@@ -1,7 +1,13 @@
-import pytest
 import re
-from spacy.util import get_lang_class
+import string
+
+import hypothesis
+import hypothesis.strategies
+import pytest
+
+import spacy
 from spacy.tokenizer import Tokenizer
+from spacy.util import get_lang_class
 
 # Only include languages with no external dependencies
 # "is" seems to confuse importlib, so we're also excluding it for now
@@ -77,3 +83,46 @@ def test_tokenizer_explain_special_matcher(en_vocab):
     tokens = [t.text for t in tokenizer("a/a.")]
     explain_tokens = [t[1] for t in tokenizer.explain("a/a.")]
     assert tokens == explain_tokens
+
+
+@hypothesis.strategies.composite
+def sentence_strategy(draw: hypothesis.strategies.DrawFn, max_n_words: int = 4) -> str:
+    """
+    Composite strategy for fuzzily generating sentence with varying interpunctation.
+
+    draw (hypothesis.strategies.DrawFn): Protocol for drawing function allowing to fuzzily pick from hypothesis'
+                                         strategies.
+    max_n_words (int): Max. number of words in generated sentence.
+    RETURNS (str): Fuzzily generated sentence.
+    """
+
+    punctuation_and_space_regex = "|".join(
+        [*[re.escape(p) for p in string.punctuation], r"\s"]
+    )
+    sentence = [
+        [
+            draw(hypothesis.strategies.text(min_size=1)),
+            draw(hypothesis.strategies.from_regex(punctuation_and_space_regex)),
+        ]
+        for _ in range(
+            draw(hypothesis.strategies.integers(min_value=2, max_value=max_n_words))
+        )
+    ]
+
+    return " ".join([token for token_pair in sentence for token in token_pair])
+
+
+@pytest.mark.xfail
+@pytest.mark.parametrize("lang", LANGUAGES)
+@hypothesis.given(sentence=sentence_strategy())
+def test_tokenizer_explain_fuzzy(lang: str, sentence: str) -> None:
+    """
+    Tests whether output of tokenizer.explain() matches tokenizer output. Input generated by hypothesis.
+    lang (str): Language to test.
+    text (str): Fuzzily generated sentence to tokenize.
+    """
+
+    tokenizer: Tokenizer = spacy.blank(lang).tokenizer
+    tokens = [t.text for t in tokenizer(sentence) if not t.is_space]
+    debug_tokens = [t[1] for t in tokenizer.explain(sentence)]
+    assert tokens == debug_tokens, f"{tokens}, {debug_tokens}, {sentence}"