Merge branch 'feature/coref' into fix/coref-alignment

Had to renumber error message.

.github/azure-steps.yml

@@ -64,12 +64,12 @@ steps:
     displayName: "Run GPU tests"
     condition: eq(${{ parameters.gpu }}, true)
 
-  - script: |
+#  - script: |
-      python -m spacy download ca_core_news_sm
+#      python -m spacy download ca_core_news_sm
-      python -m spacy download ca_core_news_md
+#      python -m spacy download ca_core_news_md
-      python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
+#      python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
-    displayName: 'Test download CLI'
+#    displayName: 'Test download CLI'
-    condition: eq(variables['python_version'], '3.8')
+#    condition: eq(variables['python_version'], '3.8')
 
   - script: |
       python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
@@ -93,17 +93,17 @@ steps:
     displayName: 'Test train CLI'
     condition: eq(variables['python_version'], '3.8')
 
-  - script: |
+#  - script: |
-      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
+#      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
-      PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
+#      PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
-    displayName: 'Test assemble CLI'
+#    displayName: 'Test assemble CLI'
-    condition: eq(variables['python_version'], '3.8')
+#    condition: eq(variables['python_version'], '3.8')
-
+#
-  - script: |
+#  - script: |
-      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
+#      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
-      python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
+#      python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
-    displayName: 'Test assemble CLI vectors warning'
+#    displayName: 'Test assemble CLI vectors warning'
-    condition: eq(variables['python_version'], '3.8')
+#    condition: eq(variables['python_version'], '3.8')
 
   - script: |
       python .github/validate_universe_json.py website/meta/universe.json
@@ -111,7 +111,7 @@ 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/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"

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 3.3.1 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)

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.

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>=8.1.0.dev0,<8.2.0",
+    "thinc>=8.1.0.dev3,<8.2.0",
-    "blis>=0.9.0,<0.10.0",
     "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>=8.1.0.dev0,<8.2.0
+thinc>=8.1.0.dev3,<8.2.0
-blis>=0.9.0,<0.10.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.1.0
@@ -22,7 +21,7 @@ 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

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>=8.1.0.dev0,<8.2.0
+    thinc>=8.1.0.dev3,<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>=8.1.0.dev0,<8.2.0
+    thinc>=8.1.0.dev3,<8.2.0
-    blis>=0.9.0,<0.10.0
     wasabi>=0.9.1,<1.1.0
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
@@ -62,7 +61,7 @@ install_requires =
     # 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]
@@ -105,7 +104,7 @@ cuda114 =
 cuda115 =
     cupy-cuda115>=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

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__ = "3.4.0"
 __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
 
@@ -554,5 +554,5 @@ 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

@@ -10,7 +10,7 @@ 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
@@ -361,7 +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(
@@ -758,9 +758,9 @@ 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
@@ -908,7 +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)
             ]

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/errors.py

@@ -204,6 +204,11 @@ class Warnings(metaclass=ErrorsWithCodes):
             "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}")
 
 
 class Errors(metaclass=ErrorsWithCodes):
@@ -532,6 +537,8 @@ 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}.")
@@ -903,8 +910,8 @@ 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}")
@@ -919,7 +926,15 @@ class Errors(metaclass=ErrorsWithCodes):
     E1035 = ("Token index {i} out of bounds ({length})")
     E1036 = ("Cannot index into NoneNode")
     E1037 = ("Invalid attribute value '{attr}'.")
-    E1038 = ("Misalignment in coref. Head token has no match in training doc.")
+    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 = ("Misalignment in coref. Head token has no match in training doc.")
 
 
 # Deprecated model shortcuts, only used in errors and warnings

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/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"] = [
@@ -139,26 +139,27 @@ 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()]:
-        _exc[orth + "'s"] = [
+        if morph != "Number=Plur|Person=3":
-            {ORTH: orth, NORM: word},
+            _exc[orth + "'s"] = [
-            {ORTH: "'s", NORM: "'s"},
+                {ORTH: orth, NORM: word},
-        ]
+                {ORTH: "'s", NORM: "'s"},
+            ]
 
-        _exc[orth + "s"] = [{ORTH: orth, NORM: word}, {ORTH: "s"}]
+            _exc[orth + "s"] = [{ORTH: orth, NORM: word}, {ORTH: "s"}]
 
         _exc[orth + "'ll"] = [
             {ORTH: orth, NORM: word},
@@ -182,25 +183,26 @@ for word in [
             {ORTH: "ve", NORM: "have"},
         ]
 
-        _exc[orth + "'re"] = [
+        if morph != "Number=Sing|Person=3":
-            {ORTH: orth, NORM: word},
+            _exc[orth + "'re"] = [
-            {ORTH: "'re", NORM: "are"},
+                {ORTH: orth, NORM: word},
-        ]
+                {ORTH: "'re", NORM: "are"},
+            ]
 
-        _exc[orth + "re"] = [
+            _exc[orth + "re"] = [
-            {ORTH: orth, NORM: word},
+                {ORTH: orth, NORM: word},
-            {ORTH: "re", NORM: "are"},
+                {ORTH: "re", NORM: "are"},
-        ]
+            ]
 
-        _exc[orth + "'ve"] = [
+            _exc[orth + "'ve"] = [
-            {ORTH: orth, NORM: word},
+                {ORTH: orth, NORM: word},
-            {ORTH: "'ve"},
+                {ORTH: "'ve"},
-        ]
+            ]
 
-        _exc[orth + "ve"] = [
+            _exc[orth + "ve"] = [
-            {ORTH: orth},
+                {ORTH: orth},
-            {ORTH: "ve", NORM: "have"},
+                {ORTH: "ve", NORM: "have"},
-        ]
+            ]
 
         _exc[orth + "'d"] = [
             {ORTH: orth, NORM: word},

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
 
@@ -1090,16 +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
@@ -1519,7 +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 = (
@@ -1597,8 +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
@@ -1618,7 +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)
         ]
@@ -1631,12 +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)
@@ -1671,6 +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,
@@ -1685,6 +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.
@@ -1838,8 +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:
@@ -1991,6 +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],
@@ -2163,7 +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,
@@ -2184,17 +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/ml/_precomputable_affine.py

@@ -22,9 +22,11 @@ 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))
+    Yf[0] = model.get_param("pad")
 
     def backward(dY_ids):
         # This backprop is particularly tricky, because we get back a different

spacy/ml/models/coref.py

@@ -2,13 +2,16 @@ from typing import List, Tuple
 
 from thinc.api import Model, chain
 from thinc.api import PyTorchWrapper, ArgsKwargs
-from thinc.types import Floats2d, Ints2d, Ints1d
+from thinc.types import Floats2d
 from thinc.util import torch, xp2torch, torch2xp
 
 from ...tokens import Doc
 from ...util import registry
 
 
+EPSILON = 1e-7
+
+
 @registry.architectures("spacy.Coref.v1")
 def build_wl_coref_model(
     tok2vec: Model[List[Doc], List[Floats2d]],
@@ -42,7 +45,9 @@ def build_wl_coref_model(
     return coref_model
 
 
-def convert_coref_clusterer_inputs(model: Model, X: List[Floats2d], is_train: bool):
+def convert_coref_clusterer_inputs(
+        model: Model, X: List[Floats2d], is_train: bool
+):
     # The input here is List[Floats2d], one for each doc
     # just use the first
     # TODO real batching
@@ -50,7 +55,7 @@ def convert_coref_clusterer_inputs(model: Model, X: List[Floats2d], is_train: bo
     word_features = xp2torch(X, requires_grad=is_train)
 
     # TODO fix or remove type annotations
-    def backprop(args: ArgsKwargs): #-> List[Floats2d]:
+    def backprop(args: ArgsKwargs):  #-> List[Floats2d]:
         # convert to xp and wrap in list
         gradients = torch2xp(args.args[0])
         return [gradients]
@@ -58,7 +63,9 @@ def convert_coref_clusterer_inputs(model: Model, X: List[Floats2d], is_train: bo
     return ArgsKwargs(args=(word_features,), kwargs={}), backprop
 
 
-def convert_coref_clusterer_outputs(model: Model, inputs_outputs, is_train: bool):
+def convert_coref_clusterer_outputs(
+        model: Model, inputs_outputs, is_train: bool
+):
     _, outputs = inputs_outputs
     scores, indices = outputs
 
@@ -149,10 +156,10 @@ class CorefClusterer(torch.nn.Module):
         a_scores_lst: List[torch.Tensor] = []
 
         for i in range(0, len(words), batch_size):
-            pw_batch = pw[i : i + batch_size]
+            pw_batch = pw[i:i + batch_size]
-            words_batch = words[i : i + batch_size]
+            words_batch = words[i:i + batch_size]
-            top_indices_batch = top_indices[i : i + batch_size]
+            top_indices_batch = top_indices[i:i + batch_size]
-            top_rough_scores_batch = top_rough_scores[i : i + batch_size]
+            top_rough_scores_batch = top_rough_scores[i:i + batch_size]
 
             # a_scores_batch    [batch_size, n_ants]
             a_scores_batch = self.a_scorer(
@@ -168,7 +175,6 @@ class CorefClusterer(torch.nn.Module):
         return coref_scores, top_indices
 
 
-EPSILON = 1e-7
 # Note this function is kept here to keep a torch dep out of coref_util.
 def add_dummy(tensor: torch.Tensor, eps: bool = False):
     """Prepends zeros (or a very small value if eps is True)
@@ -294,7 +300,7 @@ class RoughScorer(torch.nn.Module):
         self.k = antecedent_limit
 
     def forward(
-        self,  # type: ignore  # pylint: disable=arguments-differ  #35566 in pytorch
+        self,  # type: ignore
         mentions: torch.Tensor,
     ) -> Tuple[torch.Tensor, torch.Tensor]:
         """
@@ -305,6 +311,7 @@ class RoughScorer(torch.nn.Module):
         pair_mask = torch.arange(mentions.shape[0])
         pair_mask = pair_mask.unsqueeze(1) - pair_mask.unsqueeze(0)
         pair_mask = torch.log((pair_mask > 0).to(torch.float))
+        pair_mask = pair_mask.to(mentions.device)
         bilinear_scores = self.dropout(self.bilinear(mentions)).mm(mentions.T)
         rough_scores = pair_mask + bilinear_scores
         top_scores, indices = torch.topk(
@@ -340,5 +347,6 @@ class DistancePairwiseEncoder(torch.nn.Module):
         log_distance = distance.to(torch.float).log2().floor_()
         log_distance = log_distance.clamp_max_(max=6).to(torch.long)
         distance = torch.where(distance < 5, distance - 1, log_distance + 2)
+        distance = distance.to(top_indices.device)
         distance = self.distance_emb(distance)
         return self.dropout(distance)

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))
+            >> 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/span_predictor.py

@@ -182,11 +182,12 @@ class SpanPredictor(torch.nn.Module):
             torch.Tensor: span start/end scores, (n_heads x n_words x 2)
         """
         # If we don't receive heads, return empty
+        device = heads_ids.device
         if heads_ids.nelement() == 0:
             return torch.empty(size=(0,))
         # Obtain distance embedding indices, [n_heads, n_words]
         relative_positions = heads_ids.unsqueeze(1) - torch.arange(
-            words.shape[0]
+            words.shape[0], device=device
         ).unsqueeze(0)
         md = self.max_distance
         # make all valid distances positive
@@ -210,20 +211,26 @@ class SpanPredictor(torch.nn.Module):
             dim=1,
         )
         lengths = same_sent.sum(dim=1)
-        padding_mask = torch.arange(0, lengths.max().item()).unsqueeze(0)
+        padding_mask = torch.arange(
+            0, lengths.max().item(), device=device
+        ).unsqueeze(0)
         # (n_heads x max_sent_len)
         padding_mask = padding_mask < lengths.unsqueeze(1)
         # (n_heads x max_sent_len x input_size * 2 + distance_emb_size)
         # This is necessary to allow the convolution layer to look at several
         # word scores
-        padded_pairs = torch.zeros(*padding_mask.shape, pair_matrix.shape[-1])
+        padded_pairs = torch.zeros(
+            *padding_mask.shape, pair_matrix.shape[-1], device=device
+        )
         padded_pairs[padding_mask] = pair_matrix
         res = self.ffnn(padded_pairs)  # (n_heads x n_candidates x last_layer_output)
         res = self.conv(res.permute(0, 2, 1)).permute(
             0, 2, 1
         )  # (n_heads x n_candidates, 2)
 
-        scores = torch.full((heads_ids.shape[0], words.shape[0], 2), float("-inf"))
+        scores = torch.full(
+            (heads_ids.shape[0], words.shape[0], 2), float("-inf"), device=device
+        )
         scores[rows, cols] = res[padding_mask]
         # Make sure that start <= head <= end during inference
         if not self.training:

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 = get_ops("cpu").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/pipeline/__init__.py

@@ -15,6 +15,7 @@ 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
@@ -32,6 +33,7 @@ __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
@@ -58,32 +61,56 @@ cdef bool _is_nonproj_arc(int tokenid, const vector[int]& heads) nogil:
         return False
     elif head < 0:  # unattached tokens cannot be non-projective
         return False
-    
+
     cdef int start, end
     if head < tokenid:
         start, end = (head+1, tokenid)
     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/coref.py

@@ -276,7 +276,7 @@ class CoreferenceResolver(TrainablePipe):
                 span = example.predicted.char_span(start_char, end_char)
                 if span is None:
                     # TODO log more details
-                    raise IndexError(Errors.E1038)
+                    raise IndexError(Errors.E1043)
                 cc.append( (span.start, span.end) )
             clusters.append(cc)
 

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/entity_linker.py

@@ -355,7 +355,7 @@ 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 there are no matches, short circuit
@@ -368,13 +368,12 @@ class EntityLinker(TrainablePipe):
                 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
 
@@ -391,18 +390,21 @@ 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)
-                # Looping through each entity (TODO: rewrite)
+            for ent in doc.ents:
-                for ent in doc.ents:
+                sent_index = sentences.index(ent.sent)
-                    sent = ent.sent
+                assert sent_index >= 0
-                    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)
@@ -410,55 +412,53 @@ 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
+                    sentence_encoding = self.model.predict([sent_doc])[0]
-                    if self.incl_context:
+                    sentence_encoding_t = sentence_encoding.T
-                        sentence_encoding = self.model.predict([sent_doc])[0]
+                    sentence_norm = xp.linalg.norm(sentence_encoding_t)
-                        sentence_encoding_t = sentence_encoding.T
+                entity_count += 1
-                        sentence_norm = xp.linalg.norm(sentence_encoding_t)
+                if ent.label_ in self.labels_discard:
-                    entity_count += 1
+                    # ignoring this entity - setting to NIL
-                    if ent.label_ in self.labels_discard:
+                    final_kb_ids.append(self.NIL)
-                        # ignoring this entity - setting to NIL
+                else:
+                    candidates = list(self.get_candidates(self.kb, ent))
+                    if not candidates:
+                        # no prediction possible for this entity - setting to NIL
                         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:
-                        candidates = list(self.get_candidates(self.kb, ent))
+                        random.shuffle(candidates)
-                        if not candidates:
+                        # set all prior probabilities to 0 if incl_prior=False
-                            # no prediction possible for this entity - setting to NIL
+                        prior_probs = xp.asarray([c.prior_prob for c in candidates])
-                            final_kb_ids.append(self.NIL)
+                        if not self.incl_prior:
-                        elif len(candidates) == 1:
+                            prior_probs = xp.asarray([0.0 for _ in candidates])
-                            # shortcut for efficiency reasons: take the 1 candidate
+                        scores = prior_probs
-                            # TODO: thresholding
+                        # add in similarity from the context
-                            final_kb_ids.append(candidates[0].entity_)
+                        if self.incl_context:
-                        else:
+                            entity_encodings = xp.asarray(
-                            random.shuffle(candidates)
+                                [c.entity_vector for c in candidates]
-                            # set all prior probabilities to 0 if incl_prior=False
+                            )
-                            prior_probs = xp.asarray([c.prior_prob for c in candidates])
+                            entity_norm = xp.linalg.norm(entity_encodings, axis=1)
-                            if not self.incl_prior:
+                            if len(entity_encodings) != len(prior_probs):
-                                prior_probs = xp.asarray([0.0 for _ in candidates])
+                                raise RuntimeError(
-                            scores = prior_probs
+                                    Errors.E147.format(
-                            # add in similarity from the context
+                                        method="predict",
-                            if self.incl_context:
+                                        msg="vectors not of equal length",
-                                entity_encodings = xp.asarray(
-                                    [c.entity_vector for c in candidates]
-                                )
-                                entity_norm = xp.linalg.norm(entity_encodings, axis=1)
-                                if len(entity_encodings) != len(prior_probs):
-                                    raise RuntimeError(
-                                        Errors.E147.format(
-                                            method="predict",
-                                            msg="vectors not of equal length",
-                                        )
                                     )
-                                # cosine similarity
-                                sims = xp.dot(entity_encodings, sentence_encoding_t) / (
-                                    sentence_norm * entity_norm
                                 )
-                                if sims.shape != prior_probs.shape:
+                            # cosine similarity
-                                    raise ValueError(Errors.E161)
+                            sims = xp.dot(entity_encodings, sentence_encoding_t) / (
-                                scores = prior_probs + sims - (prior_probs * sims)
+                                sentence_norm * entity_norm
-                            # TODO: thresholding
+                            )
-                            best_index = scores.argmax().item()
+                            if sims.shape != prior_probs.shape:
-                            best_candidate = candidates[best_index]
+                                raise ValueError(Errors.E161)
-                            final_kb_ids.append(best_candidate.entity_)
+                            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_)
         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

@@ -179,10 +179,7 @@ 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)
@@ -356,7 +353,9 @@ 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/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/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
 from thinc.extra.search cimport Beam
 import numpy.random
 import numpy
@@ -259,6 +259,12 @@ 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 = get_ops("cpu").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 +275,7 @@ 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 +302,13 @@ 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

@@ -485,3 +485,29 @@ 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/scorer.py

@@ -916,6 +916,10 @@ class Scorer:
             ref = eg.reference
             pred = eg.predicted
             for key, gold_sg in ref.spans.items():
+                #TODO it might be better to do something like pred.spans.get(key, [])
+                if len(gold_sg) == 0:
+                    # if there are no spans there's nothing to predict
+                    continue
                 if key.startswith(output_prefix):
                     pred_sg = pred.spans[key]
                     for gold_mention, pred_mention in zip(gold_sg, pred_sg):
@@ -924,6 +928,9 @@ class Scorer:
                         pred_starts.append(pred_mention.start)
                         pred_ends.append(pred_mention.end)
 
+            # it's possible there are no heads to predict from, in which case, skip
+            if len(starts) == 0:
+                continue
 
             # see how many are perfect
             cs = [a == b for a, b in zip(starts, pred_starts)]
@@ -933,7 +940,13 @@ class Scorer:
 
             scores.append(float(accuracy))
         out_key = f"span_{output_prefix}_accuracy"
-        return {out_key: mean(scores)}
+
+        # it is possible there was nothing to score
+        final = 0.0
+        if len(scores) > 0:
+            final = mean(scores)
+
+        return {out_key: final}
 
 
 def get_ner_prf(examples: Iterable[Example], **kwargs) -> Dict[str, Any]:

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/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/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

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/pipeline/test_entity_linker.py

@@ -1076,12 +1076,23 @@ def test_no_gold_ents(patterns):
     # this will run the pipeline on the examples and shouldn't crash
     results = 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"])
+    doc1 = Doc(
-    doc2 = Doc(nlp.vocab, words=["Kirby", "123", "456"], spaces=[True, False, False], ents=["B-CHARACTER", "B-CARDINAL", "B-CARDINAL"])
+        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]

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"
-    ruler.remove("acme")
+    if isinstance(ruler, EntityRuler):
-    doc = ruler(nlp.make_doc("Duygu founded her company ACME"))
+        ruler.remove("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("acme")
+        ruler.remove("dina")
-    ruler.remove("bday")
+        ruler.remove("acme")
-    doc = ruler(nlp.make_doc("Duygu went to school"))
+        ruler.remove("bday")
+    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
-    ruler.remove("acme")
+    if isinstance(ruler, EntityRuler):
+        ruler.remove("acme")
+    else:
+        ruler.remove_by_id("acme")
     assert len(ruler.patterns) == 1
-    ruler.remove("bday")
+    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"
-    ruler.remove("ttime")
+    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
-    ruler.remove("ttime")
+    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_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/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

@@ -589,6 +589,7 @@ def test_string_to_list_intify(value):
     assert string_to_list(value, intify=True) == [1, 2, 3]
 
 
+@pytest.mark.skip(reason="Temporarily skip for dev version")
 def test_download_compatibility():
     spec = SpecifierSet("==" + about.__version__)
     spec.prereleases = False
@@ -599,6 +600,7 @@ def test_download_compatibility():
         assert get_minor_version(about.__version__) == get_minor_version(version)
 
 
+@pytest.mark.skip(reason="Temporarily skip for dev version")
 def test_validate_compatibility_table():
     spec = SpecifierSet("==" + about.__version__)
     spec.prereleases = False

spacy/tests/training/test_readers.py

@@ -60,11 +60,12 @@ def test_readers():
     assert isinstance(extra_corpus, Callable)
 
 
+# TODO: enable IMDB test once Stanford servers are back up and running
 @pytest.mark.slow
 @pytest.mark.parametrize(
     "reader,additional_config",
     [
-        ("ml_datasets.imdb_sentiment.v1", {"train_limit": 10, "dev_limit": 10}),
+        #        ("ml_datasets.imdb_sentiment.v1", {"train_limit": 10, "dev_limit": 10}),
         ("ml_datasets.dbpedia.v1", {"train_limit": 10, "dev_limit": 10}),
         ("ml_datasets.cmu_movies.v1", {"limit": 10, "freq_cutoff": 200, "split": 0.8}),
     ],

spacy/tests/training/test_training.py

@@ -671,13 +671,13 @@ def test_gold_ner_missing_tags(en_tokenizer):
 
 def test_projectivize(en_tokenizer):
     doc = en_tokenizer("He pretty quickly walks away")
-    heads = [3, 2, 3, 0, 2]
+    heads = [3, 2, 3, 3, 2]
     deps = ["dep"] * len(heads)
     example = Example.from_dict(doc, {"heads": heads, "deps": deps})
     proj_heads, proj_labels = example.get_aligned_parse(projectivize=True)
     nonproj_heads, nonproj_labels = example.get_aligned_parse(projectivize=False)
-    assert proj_heads == [3, 2, 3, 0, 3]
+    assert proj_heads == [3, 2, 3, 3, 3]
-    assert nonproj_heads == [3, 2, 3, 0, 2]
+    assert nonproj_heads == [3, 2, 3, 3, 2]
 
 
 def test_iob_to_biluo():

spacy/tests/util.py

@@ -5,6 +5,7 @@ import srsly
 from spacy.tokens import Doc
 from spacy.vocab import Vocab
 from spacy.util import make_tempdir  # noqa: F401
+from spacy.training import split_bilu_label
 from thinc.api import get_current_ops
 
 
@@ -40,7 +41,7 @@ def apply_transition_sequence(parser, doc, sequence):
     desired state."""
     for action_name in sequence:
         if "-" in action_name:
-            move, label = action_name.split("-")
+            move, label = split_bilu_label(action_name)
             parser.add_label(label)
     with parser.step_through(doc) as stepwise:
         for transition in sequence:

spacy/tokens/_dict_proxies.py

@@ -1,10 +1,11 @@
-from typing import Iterable, Tuple, Union, Optional, TYPE_CHECKING
+from typing import Dict, Iterable, List, Tuple, Union, Optional, TYPE_CHECKING
+import warnings
 import weakref
 from collections import UserDict
 import srsly
 
 from .span_group import SpanGroup
-from ..errors import Errors
+from ..errors import Errors, Warnings
 
 
 if TYPE_CHECKING:
@@ -16,7 +17,7 @@ if TYPE_CHECKING:
 # Why inherit from UserDict instead of dict here?
 # Well, the 'dict' class doesn't necessarily delegate everything nicely,
 # for performance reasons. The UserDict is slower but better behaved.
-# See https://treyhunner.com/2019/04/why-you-shouldnt-inherit-from-list-and-dict-in-python/0ww
+# See https://treyhunner.com/2019/04/why-you-shouldnt-inherit-from-list-and-dict-in-python/
 class SpanGroups(UserDict):
     """A dict-like proxy held by the Doc, to control access to span groups."""
 
@@ -53,20 +54,52 @@ class SpanGroups(UserDict):
         return super().setdefault(key, default=default)
 
     def to_bytes(self) -> bytes:
-        # We don't need to serialize this as a dict, because the groups
+        # We serialize this as a dict in order to track the key(s) a SpanGroup
-        # know their names.
+        # is a value of (in a backward- and forward-compatible way), since
+        # a SpanGroup can have a key that doesn't match its `.name` (See #10685)
         if len(self) == 0:
             return self._EMPTY_BYTES
-        msg = [value.to_bytes() for value in self.values()]
+        msg: Dict[bytes, List[str]] = {}
+        for key, value in self.items():
+            msg.setdefault(value.to_bytes(), []).append(key)
         return srsly.msgpack_dumps(msg)
 
     def from_bytes(self, bytes_data: bytes) -> "SpanGroups":
-        msg = [] if bytes_data == self._EMPTY_BYTES else srsly.msgpack_loads(bytes_data)
+        # backwards-compatibility: bytes_data may be one of:
+        # b'', a serialized empty list, a serialized list of SpanGroup bytes
+        # or a serialized dict of SpanGroup bytes -> keys
+        msg = (
+            []
+            if not bytes_data or bytes_data == self._EMPTY_BYTES
+            else srsly.msgpack_loads(bytes_data)
+        )
         self.clear()
         doc = self._ensure_doc()
-        for value_bytes in msg:
+        if isinstance(msg, list):
-            group = SpanGroup(doc).from_bytes(value_bytes)
+            # This is either the 1st version of `SpanGroups` serialization
-            self[group.name] = group
+            # or there were no SpanGroups serialized
+            for value_bytes in msg:
+                group = SpanGroup(doc).from_bytes(value_bytes)
+                if group.name in self:
+                    # Display a warning if `msg` contains `SpanGroup`s
+                    # that have the same .name (attribute).
+                    # Because, for `SpanGroups` serialized as lists,
+                    # only 1 SpanGroup per .name is loaded. (See #10685)
+                    warnings.warn(
+                        Warnings.W120.format(
+                            group_name=group.name, group_values=self[group.name]
+                        )
+                    )
+                self[group.name] = group
+        else:
+            for value_bytes, keys in msg.items():
+                group = SpanGroup(doc).from_bytes(value_bytes)
+                # Deserialize `SpanGroup`s as copies because it's possible for two
+                # different `SpanGroup`s (pre-serialization) to have the same bytes
+                # (since they can have the same `.name`).
+                self[keys[0]] = group
+                for key in keys[1:]:
+                    self[key] = group.copy()
         return self
 
     def _ensure_doc(self) -> "Doc":

spacy/tokens/doc.pyi

@@ -170,6 +170,9 @@ class Doc:
     def extend_tensor(self, tensor: Floats2d) -> None: ...
     def retokenize(self) -> Retokenizer: ...
     def to_json(self, underscore: Optional[List[str]] = ...) -> Dict[str, Any]: ...
+    def from_json(
+        self, doc_json: Dict[str, Any] = ..., validate: bool = False
+    ) -> Doc: ...
     def to_utf8_array(self, nr_char: int = ...) -> Ints2d: ...
     @staticmethod
     def _get_array_attrs() -> Tuple[Any]: ...

spacy/tokens/doc.pyx

@@ -1,4 +1,6 @@
 # cython: infer_types=True, bounds_check=False, profile=True
+from typing import Set
+
 cimport cython
 cimport numpy as np
 from libc.string cimport memcpy
@@ -31,10 +33,11 @@ from ..errors import Errors, Warnings
 from ..morphology import Morphology
 from .. import util
 from .. import parts_of_speech
+from .. import schemas
 from .underscore import Underscore, get_ext_args
 from ._retokenize import Retokenizer
 from ._serialize import ALL_ATTRS as DOCBIN_ALL_ATTRS
-
+from ..util import get_words_and_spaces
 
 DEF PADDING = 5
 
@@ -516,7 +519,7 @@ cdef class Doc:
     def doc(self):
         return self
 
-    def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, alignment_mode="strict"):
+    def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, alignment_mode="strict", span_id=0):
         """Create a `Span` object from the slice
         `doc.text[start_idx : end_idx]`. Returns None if no valid `Span` can be
         created.
@@ -575,7 +578,7 @@ cdef class Doc:
                 start += 1
         # Currently we have the token index, we want the range-end index
         end += 1
-        cdef Span span = Span(self, start, end, label=label, kb_id=kb_id, vector=vector)
+        cdef Span span = Span(self, start, end, label=label, kb_id=kb_id, span_id=span_id, vector=vector)
         return span
 
     def similarity(self, other):
@@ -713,6 +716,7 @@ cdef class Doc:
             cdef int start = -1
             cdef attr_t label = 0
             cdef attr_t kb_id = 0
+            cdef attr_t ent_id = 0
             output = []
             for i in range(self.length):
                 token = &self.c[i]
@@ -723,18 +727,20 @@ cdef class Doc:
                 elif token.ent_iob == 2 or token.ent_iob == 0 or \
                         (token.ent_iob == 3 and token.ent_type == 0):
                     if start != -1:
-                        output.append(Span(self, start, i, label=label, kb_id=kb_id))
+                        output.append(Span(self, start, i, label=label, kb_id=kb_id, span_id=ent_id))
                     start = -1
                     label = 0
                     kb_id = 0
+                    ent_id = 0
                 elif token.ent_iob == 3:
                     if start != -1:
-                        output.append(Span(self, start, i, label=label, kb_id=kb_id))
+                        output.append(Span(self, start, i, label=label, kb_id=kb_id, span_id=ent_id))
                     start = i
                     label = token.ent_type
                     kb_id = token.ent_kb_id
+                    ent_id = token.ent_id
             if start != -1:
-                output.append(Span(self, start, self.length, label=label, kb_id=kb_id))
+                output.append(Span(self, start, self.length, label=label, kb_id=kb_id, span_id=ent_id))
             # remove empty-label spans
             output = [o for o in output if o.label_ != ""]
             return tuple(output)
@@ -743,14 +749,14 @@ cdef class Doc:
             # TODO:
             # 1. Test basic data-driven ORTH gazetteer
             # 2. Test more nuanced date and currency regex
-            cdef attr_t entity_type, kb_id
+            cdef attr_t entity_type, kb_id, ent_id
             cdef int ent_start, ent_end
             ent_spans = []
             for ent_info in ents:
-                entity_type_, kb_id, ent_start, ent_end = get_entity_info(ent_info)
+                entity_type_, kb_id, ent_start, ent_end, ent_id = get_entity_info(ent_info)
                 if isinstance(entity_type_, str):
                     self.vocab.strings.add(entity_type_)
-                span = Span(self, ent_start, ent_end, label=entity_type_, kb_id=kb_id)
+                span = Span(self, ent_start, ent_end, label=entity_type_, kb_id=kb_id, span_id=ent_id)
                 ent_spans.append(span)
             self.set_ents(ent_spans, default=SetEntsDefault.outside)
 
@@ -801,6 +807,9 @@ cdef class Doc:
                     self.c[i].ent_iob = 1
                 self.c[i].ent_type = span.label
                 self.c[i].ent_kb_id = span.kb_id
+                # for backwards compatibility in v3, only set ent_id from
+                # span.id if it's set, otherwise don't override
+                self.c[i].ent_id = span.id if span.id else self.c[i].ent_id
         for span in blocked:
             for i in range(span.start, span.end):
                 self.c[i].ent_iob = 3
@@ -1180,6 +1189,7 @@ cdef class Doc:
                             span.end_char + char_offset,
                             span.label,
                             span.kb_id,
+                            span.id,
                             span.text, # included as a check
                         ))
             char_offset += len(doc.text)
@@ -1215,8 +1225,9 @@ cdef class Doc:
                         span_tuple[1],
                         label=span_tuple[2],
                         kb_id=span_tuple[3],
+                        span_id=span_tuple[4],
                 )
-                text = span_tuple[4]
+                text = span_tuple[5]
                 if span is not None and span.text == text:
                     concat_doc.spans[key].append(span)
                 else:
@@ -1467,6 +1478,138 @@ cdef class Doc:
                 remove_label_if_necessary(attributes[i])
                 retokenizer.merge(span, attributes[i])
 
+    def from_json(self, doc_json, *, validate=False):
+        """Convert a JSON document generated by Doc.to_json() to a Doc.
+
+        doc_json (Dict): JSON representation of doc object to load.
+        validate (bool): Whether to validate `doc_json` against the expected schema.
+            Defaults to False.
+        RETURNS (Doc): A doc instance corresponding to the specified JSON representation.
+        """
+
+        if validate:
+            schema_validation_message = schemas.validate(schemas.DocJSONSchema, doc_json)
+            if schema_validation_message:
+                raise ValueError(Errors.E1038.format(message=schema_validation_message))
+
+        ### Token-level properties ###
+
+        words = []
+        token_attrs_ids = (POS, HEAD, DEP, LEMMA, TAG, MORPH)
+        # Map annotation type IDs to their string equivalents.
+        token_attrs = {t: self.vocab.strings[t].lower() for t in token_attrs_ids}
+        token_annotations = {}
+
+        # Gather token-level properties.
+        for token_json in doc_json["tokens"]:
+            words.append(doc_json["text"][token_json["start"]:token_json["end"]])
+            for attr, attr_json in token_attrs.items():
+                if attr_json in token_json:
+                    if token_json["id"] == 0 and attr not in token_annotations:
+                        token_annotations[attr] = []
+                    elif attr not in token_annotations:
+                        raise ValueError(Errors.E1040.format(partial_attrs=attr))
+                    token_annotations[attr].append(token_json[attr_json])
+
+        # Initialize doc instance.
+        start = 0
+        cdef const LexemeC* lex
+        cdef bint has_space
+        reconstructed_words, spaces = get_words_and_spaces(words, doc_json["text"])
+        assert words == reconstructed_words
+
+        for word, has_space in zip(words, spaces):
+            lex = self.vocab.get(self.mem, word)
+            self.push_back(lex, has_space)
+
+        # Set remaining token-level attributes via Doc.from_array().
+        if HEAD in token_annotations:
+            token_annotations[HEAD] = [
+                head - i for i, head in enumerate(token_annotations[HEAD])
+            ]
+
+        if DEP in token_annotations and HEAD not in token_annotations:
+            token_annotations[HEAD] = [0] * len(token_annotations[DEP])
+        if HEAD in token_annotations and DEP not in token_annotations:
+            raise ValueError(Errors.E1017)
+        if POS in token_annotations:
+            for pp in set(token_annotations[POS]):
+                if pp not in parts_of_speech.IDS:
+                    raise ValueError(Errors.E1021.format(pp=pp))
+
+        # Collect token attributes, assert all tokens have exactly the same set of attributes.
+        attrs = []
+        partial_attrs: Set[str] = set()
+        for attr in token_attrs.keys():
+            if attr in token_annotations:
+                if len(token_annotations[attr]) != len(words):
+                    partial_attrs.add(token_attrs[attr])
+                attrs.append(attr)
+        if len(partial_attrs):
+            raise ValueError(Errors.E1040.format(partial_attrs=partial_attrs))
+
+        # If there are any other annotations, set them.
+        if attrs:
+            array = self.to_array(attrs)
+            if array.ndim == 1:
+                array = numpy.reshape(array, (array.size, 1))
+            j = 0
+
+            for j, (attr, annot) in enumerate(token_annotations.items()):
+                if attr is HEAD:
+                    for i in range(len(words)):
+                        array[i, j] = annot[i]
+                elif attr is MORPH:
+                    for i in range(len(words)):
+                        array[i, j] = self.vocab.morphology.add(annot[i])
+                else:
+                    for i in range(len(words)):
+                        array[i, j] = self.vocab.strings.add(annot[i])
+            self.from_array(attrs, array)
+
+        ### Span/document properties ###
+
+        # Complement other document-level properties (cats, spans, ents).
+        self.cats = doc_json.get("cats", {})
+
+        # Set sentence boundaries, if dependency parser not available but sentences are specified in JSON.
+        if not self.has_annotation("DEP"):
+            for sent in doc_json.get("sents", {}):
+                char_span = self.char_span(sent["start"], sent["end"])
+                if char_span is None:
+                    raise ValueError(Errors.E1039.format(obj="sentence", start=sent["start"], end=sent["end"]))
+                char_span[0].is_sent_start = True
+                for token in char_span[1:]:
+                    token.is_sent_start = False
+
+
+        for span_group in doc_json.get("spans", {}):
+            spans = []
+            for span in doc_json["spans"][span_group]:
+                char_span = self.char_span(span["start"], span["end"], span["label"], span["kb_id"])
+                if char_span is None:
+                    raise ValueError(Errors.E1039.format(obj="span", start=span["start"], end=span["end"]))
+                spans.append(char_span)
+            self.spans[span_group] = spans
+
+        if "ents" in doc_json:
+            ents = []
+            for ent in doc_json["ents"]:
+                char_span = self.char_span(ent["start"], ent["end"], ent["label"])
+                if char_span is None:
+                    raise ValueError(Errors.E1039.format(obj="entity"), start=ent["start"], end=ent["end"])
+                ents.append(char_span)
+            self.ents = ents
+
+        # Add custom attributes. Note that only Doc extensions are currently considered, Token and Span extensions are
+        # not yet supported.
+        for attr in doc_json.get("_", {}):
+            if not Doc.has_extension(attr):
+                Doc.set_extension(attr)
+            self._.set(attr, doc_json["_"][attr])
+
+        return self
+
     def to_json(self, underscore=None):
         """Convert a Doc to JSON.
 
@@ -1477,12 +1620,10 @@ cdef class Doc:
         """
         data = {"text": self.text}
         if self.has_annotation("ENT_IOB"):
-            data["ents"] = [{"start": ent.start_char, "end": ent.end_char,
+            data["ents"] = [{"start": ent.start_char, "end": ent.end_char, "label": ent.label_} for ent in self.ents]
-                            "label": ent.label_} for ent in self.ents]
         if self.has_annotation("SENT_START"):
             sents = list(self.sents)
-            data["sents"] = [{"start": sent.start_char, "end": sent.end_char}
+            data["sents"] = [{"start": sent.start_char, "end": sent.end_char} for sent in sents]
-                             for sent in sents]
         if self.cats:
             data["cats"] = self.cats
         data["tokens"] = []
@@ -1508,7 +1649,9 @@ cdef class Doc:
             for span_group in self.spans:
                 data["spans"][span_group] = []
                 for span in self.spans[span_group]:
-                    span_data = {"start": span.start_char, "end": span.end_char, "label": span.label_, "kb_id": span.kb_id_}
+                    span_data = {
+                        "start": span.start_char, "end": span.end_char, "label": span.label_, "kb_id": span.kb_id_
+                    }
                     data["spans"][span_group].append(span_data)
 
         if underscore:
@@ -1737,18 +1880,17 @@ cdef int [:,:] _get_lca_matrix(Doc doc, int start, int end):
 def pickle_doc(doc):
     bytes_data = doc.to_bytes(exclude=["vocab", "user_data", "user_hooks"])
     hooks_and_data = (doc.user_data, doc.user_hooks, doc.user_span_hooks,
-                      doc.user_token_hooks, doc._context)
+                      doc.user_token_hooks)
     return (unpickle_doc, (doc.vocab, srsly.pickle_dumps(hooks_and_data), bytes_data))
 
 
 def unpickle_doc(vocab, hooks_and_data, bytes_data):
-    user_data, doc_hooks, span_hooks, token_hooks, _context = srsly.pickle_loads(hooks_and_data)
+    user_data, doc_hooks, span_hooks, token_hooks = srsly.pickle_loads(hooks_and_data)
 
     doc = Doc(vocab, user_data=user_data).from_bytes(bytes_data, exclude=["user_data"])
     doc.user_hooks.update(doc_hooks)
     doc.user_span_hooks.update(span_hooks)
     doc.user_token_hooks.update(token_hooks)
-    doc._context = _context
     return doc
 
 
@@ -1772,16 +1914,18 @@ def fix_attributes(doc, attributes):
 
 
 def get_entity_info(ent_info):
+    ent_kb_id = 0
+    ent_id = 0
     if isinstance(ent_info, Span):
         ent_type = ent_info.label
         ent_kb_id = ent_info.kb_id
         start = ent_info.start
         end = ent_info.end
+        ent_id = ent_info.id
     elif len(ent_info) == 3:
         ent_type, start, end = ent_info
-        ent_kb_id = 0
     elif len(ent_info) == 4:
         ent_type, ent_kb_id, start, end = ent_info
     else:
         ent_id, ent_kb_id, ent_type, start, end = ent_info
-    return ent_type, ent_kb_id, start, end
+    return ent_type, ent_kb_id, start, end, ent_id

spacy/tokens/span.pyi

@@ -48,7 +48,8 @@ class Span:
         label: Union[str, int] = ...,
         vector: Optional[Floats1d] = ...,
         vector_norm: Optional[float] = ...,
-        kb_id: Optional[int] = ...,
+        kb_id: Union[str, int] = ...,
+        span_id: Union[str, int] = ...,
     ) -> None: ...
     def __richcmp__(self, other: Span, op: int) -> bool: ...
     def __hash__(self) -> int: ...

spacy/tokens/span.pyx

@@ -80,17 +80,20 @@ cdef class Span:
         return Underscore.span_extensions.pop(name)
 
     def __cinit__(self, Doc doc, int start, int end, label=0, vector=None,
-                  vector_norm=None, kb_id=0):
+                  vector_norm=None, kb_id=0, span_id=0):
         """Create a `Span` object from the slice `doc[start : end]`.
 
         doc (Doc): The parent document.
         start (int): The index of the first token of the span.
         end (int): The index of the first token after the span.
-        label (int or str): A label to attach to the Span, e.g. for named entities.
+        label (Union[int, str]): A label to attach to the Span, e.g. for named
+            entities.
         vector (ndarray[ndim=1, dtype='float32']): A meaning representation
             of the span.
         vector_norm (float): The L2 norm of the span's vector representation.
-        kb_id (uint64): An identifier from a Knowledge Base to capture the meaning of a named entity.
+        kb_id (Union[int, str]): An identifier from a Knowledge Base to capture
+            the meaning of a named entity.
+        span_id (Union[int, str]): An identifier to associate with the span.
 
         DOCS: https://spacy.io/api/span#init
         """
@@ -101,6 +104,8 @@ cdef class Span:
             label = doc.vocab.strings.add(label)
         if isinstance(kb_id, str):
             kb_id = doc.vocab.strings.add(kb_id)
+        if isinstance(span_id, str):
+            span_id = doc.vocab.strings.add(span_id)
         if label not in doc.vocab.strings:
             raise ValueError(Errors.E084.format(label=label))
 
@@ -112,6 +117,7 @@ cdef class Span:
         self.c = SpanC(
             label=label,
             kb_id=kb_id,
+            id=span_id,
             start=start,
             end=end,
             start_char=start_char,
@@ -126,8 +132,8 @@ cdef class Span:
                 return False
             else:
                 return True
-        self_tuple = (self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id, self.doc)
+        self_tuple = (self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id, self.id, self.doc)
-        other_tuple = (other.c.start_char, other.c.end_char, other.c.label, other.c.kb_id, other.doc)
+        other_tuple = (other.c.start_char, other.c.end_char, other.c.label, other.c.kb_id, other.id, other.doc)
         # <
         if op == 0:
             return self_tuple < other_tuple
@@ -148,7 +154,7 @@ cdef class Span:
             return self_tuple >= other_tuple
 
     def __hash__(self):
-        return hash((self.doc, self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id))
+        return hash((self.doc, self.c.start_char, self.c.end_char, self.c.label, self.c.kb_id, self.c.id))
 
     def __len__(self):
         """Get the number of tokens in the span.
@@ -632,7 +638,7 @@ cdef class Span:
         else:
             return self.doc[root]
 
-    def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None):
+    def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, id=0):
         """Create a `Span` object from the slice `span.text[start : end]`.
 
         start (int): The index of the first character of the span.
@@ -774,6 +780,13 @@ cdef class Span:
         def __set__(self, attr_t kb_id):
             self.c.kb_id = kb_id
 
+    property id:
+        def __get__(self):
+            return self.c.id
+
+        def __set__(self, attr_t id):
+            self.c.id = id
+
     property ent_id:
         """RETURNS (uint64): The entity ID."""
         def __get__(self):
@@ -812,13 +825,21 @@ cdef class Span:
             self.label = self.doc.vocab.strings.add(label_)
 
     property kb_id_:
-        """RETURNS (str): The named entity's KB ID."""
+        """RETURNS (str): The span's KB ID."""
         def __get__(self):
             return self.doc.vocab.strings[self.kb_id]
 
         def __set__(self, str kb_id_):
             self.kb_id = self.doc.vocab.strings.add(kb_id_)
 
+    property id_:
+        """RETURNS (str): The span's ID."""
+        def __get__(self):
+            return self.doc.vocab.strings[self.id]
+
+        def __set__(self, str id_):
+            self.id = self.doc.vocab.strings.add(id_)
+
 
 cdef int _count_words_to_root(const TokenC* token, int sent_length) except -1:
     # Don't allow spaces to be the root, if there are

spacy/tokens/span_group.pyi

@@ -24,3 +24,4 @@ class SpanGroup:
     def __getitem__(self, i: int) -> Span: ...
     def to_bytes(self) -> bytes: ...
     def from_bytes(self, bytes_data: bytes) -> SpanGroup: ...
+    def copy(self) -> SpanGroup: ...

spacy/training/__init__.py

@@ -5,6 +5,7 @@ from .augment import dont_augment, orth_variants_augmenter  # noqa: F401
 from .iob_utils import iob_to_biluo, biluo_to_iob  # noqa: F401
 from .iob_utils import offsets_to_biluo_tags, biluo_tags_to_offsets  # noqa: F401
 from .iob_utils import biluo_tags_to_spans, tags_to_entities  # noqa: F401
+from .iob_utils import split_bilu_label, remove_bilu_prefix  # noqa: F401
 from .gold_io import docs_to_json, read_json_file  # noqa: F401
 from .batchers import minibatch_by_padded_size, minibatch_by_words  # noqa: F401
 from .loggers import console_logger  # noqa: F401

spacy/training/alignment_array.pyx

@@ -1,33 +1,39 @@
 from typing import List
 from ..errors import Errors
 import numpy
+from libc.stdint cimport int32_t
 
 
 cdef class AlignmentArray:
     """AlignmentArray is similar to Thinc's Ragged with two simplfications:
     indexing returns numpy arrays and this type can only be used for CPU arrays.
-    However, these changes make AlginmentArray more efficient for indexing in a
+    However, these changes make AlignmentArray more efficient for indexing in a
     tight loop."""
 
     __slots__ = []
 
     def __init__(self, alignment: List[List[int]]):
-        self._lengths = None
-        self._starts_ends = numpy.zeros(len(alignment) + 1, dtype="i")
-
         cdef int data_len = 0
         cdef int outer_len
         cdef int idx
+
+        self._starts_ends = numpy.zeros(len(alignment) + 1, dtype='int32')
+        cdef int32_t* starts_ends_ptr = <int32_t*>self._starts_ends.data
+
         for idx, outer in enumerate(alignment):
             outer_len = len(outer)
-            self._starts_ends[idx + 1] = self._starts_ends[idx] + outer_len
+            starts_ends_ptr[idx + 1] = starts_ends_ptr[idx] + outer_len
             data_len += outer_len
 
-        self._data = numpy.empty(data_len, dtype="i")
+        self._lengths = None
+        self._data = numpy.empty(data_len, dtype="int32")
+
         idx = 0
+        cdef int32_t* data_ptr = <int32_t*>self._data.data
+
         for outer in alignment:
             for inner in outer:
-                self._data[idx] = inner
+                data_ptr[idx] = inner
                 idx += 1
 
     def __getitem__(self, idx):

spacy/training/augment.py

@@ -3,10 +3,10 @@ from typing import Optional
 import random
 import itertools
 from functools import partial
-from pydantic import BaseModel, StrictStr
 
 from ..util import registry
 from .example import Example
+from .iob_utils import split_bilu_label
 
 if TYPE_CHECKING:
     from ..language import Language  # noqa: F401
@@ -278,10 +278,8 @@ def make_whitespace_variant(
             ent_prev = doc_dict["entities"][position - 1]
             ent_next = doc_dict["entities"][position]
             if "-" in ent_prev and "-" in ent_next:
-                ent_iob_prev = ent_prev.split("-")[0]
+                ent_iob_prev, ent_type_prev = split_bilu_label(ent_prev)
-                ent_type_prev = ent_prev.split("-", 1)[1]
+                ent_iob_next, ent_type_next = split_bilu_label(ent_next)
-                ent_iob_next = ent_next.split("-")[0]
-                ent_type_next = ent_next.split("-", 1)[1]
                 if (
                     ent_iob_prev in ("B", "I")
                     and ent_iob_next in ("I", "L")

spacy/training/example.pyx

@@ -9,11 +9,11 @@ from ..tokens.span import Span
 from ..attrs import IDS
 from .alignment import Alignment
 from .iob_utils import biluo_to_iob, offsets_to_biluo_tags, doc_to_biluo_tags
-from .iob_utils import biluo_tags_to_spans
+from .iob_utils import biluo_tags_to_spans, remove_bilu_prefix
 from ..errors import Errors, Warnings
 from ..pipeline._parser_internals import nonproj
 from ..tokens.token cimport MISSING_DEP
-from ..util import logger, to_ternary_int
+from ..util import logger, to_ternary_int, all_equal
 
 
 cpdef Doc annotations_to_doc(vocab, tok_annot, doc_annot):
@@ -151,54 +151,131 @@ cdef class Example:
                 self._y_sig = y_sig
                 return self._cached_alignment
 
+
+    def _get_aligned_vectorized(self, align, gold_values):
+        # Fast path for Doc attributes/fields that are predominantly a single value,
+        # i.e., TAG, POS, MORPH.
+        x2y_single_toks = []
+        x2y_single_toks_i = []
+
+        x2y_multiple_toks = []
+        x2y_multiple_toks_i = []
+
+        # Gather indices of gold tokens aligned to the candidate tokens into two buckets.
+        #   Bucket 1: All tokens that have a one-to-one alignment.
+        #   Bucket 2: All tokens that have a one-to-many alignment.
+        for idx, token in enumerate(self.predicted):
+            aligned_gold_i = align[token.i]
+            aligned_gold_len = len(aligned_gold_i)
+
+            if aligned_gold_len == 1:
+                x2y_single_toks.append(aligned_gold_i.item())
+                x2y_single_toks_i.append(idx)
+            elif aligned_gold_len > 1:
+                x2y_multiple_toks.append(aligned_gold_i)
+                x2y_multiple_toks_i.append(idx)
+
+        # Map elements of the first bucket directly to the output array.
+        output = numpy.full(len(self.predicted), None)
+        output[x2y_single_toks_i] = gold_values[x2y_single_toks].squeeze()
+
+        # Collapse many-to-one alignments into one-to-one alignments if they
+        # share the same value. Map to None in all other cases.
+        for i in range(len(x2y_multiple_toks)):
+            aligned_gold_values = gold_values[x2y_multiple_toks[i]]
+
+            # If all aligned tokens have the same value, use it.
+            if all_equal(aligned_gold_values):
+                x2y_multiple_toks[i] = aligned_gold_values[0].item()
+            else:
+                x2y_multiple_toks[i] = None
+
+        output[x2y_multiple_toks_i] = x2y_multiple_toks
+
+        return output.tolist()
+
+
+    def _get_aligned_non_vectorized(self, align, gold_values):
+        # Slower path for fields that return multiple values (resulting
+        # in ragged arrays that cannot be vectorized trivially).
+        output = [None] * len(self.predicted)
+
+        for token in self.predicted:
+            aligned_gold_i = align[token.i]
+            values = gold_values[aligned_gold_i].ravel()
+            if len(values) == 1:
+                output[token.i] = values.item()
+            elif all_equal(values):
+                # If all aligned tokens have the same value, use it.
+                output[token.i] = values[0].item()
+
+        return output
+
+
     def get_aligned(self, field, as_string=False):
         """Return an aligned array for a token attribute."""
         align = self.alignment.x2y
+        gold_values = self.reference.to_array([field])
+
+        if len(gold_values.shape) == 1:
+            output = self._get_aligned_vectorized(align, gold_values)
+        else:
+            output = self._get_aligned_non_vectorized(align, gold_values)
 
         vocab = self.reference.vocab
-        gold_values = self.reference.to_array([field])
-        output = [None] * len(self.predicted)
-        for token in self.predicted:
-            values = gold_values[align[token.i]]
-            values = values.ravel()
-            if len(values) == 0:
-                output[token.i] = None
-            elif len(values) == 1:
-                output[token.i] = values[0]
-            elif len(set(list(values))) == 1:
-                # If all aligned tokens have the same value, use it.
-                output[token.i] = values[0]
-            else:
-                output[token.i] = None
         if as_string and field not in ["ENT_IOB", "SENT_START"]:
             output = [vocab.strings[o] if o is not None else o for o in output]
+
         return output
 
     def get_aligned_parse(self, projectivize=True):
         cand_to_gold = self.alignment.x2y
         gold_to_cand = self.alignment.y2x
-        aligned_heads = [None] * self.x.length
-        aligned_deps = [None] * self.x.length
-        has_deps = [token.has_dep() for token in self.y]
-        has_heads = [token.has_head() for token in self.y]
         heads = [token.head.i for token in self.y]
         deps = [token.dep_ for token in self.y]
+
         if projectivize:
             proj_heads, proj_deps = nonproj.projectivize(heads, deps)
+            has_deps = [token.has_dep() for token in self.y]
+            has_heads = [token.has_head() for token in self.y]
+
             # ensure that missing data remains missing
             heads = [h if has_heads[i] else heads[i] for i, h in enumerate(proj_heads)]
             deps = [d if has_deps[i] else deps[i] for i, d in enumerate(proj_deps)]
-        for cand_i in range(self.x.length):
+
-            if cand_to_gold.lengths[cand_i] == 1:
+        # Select all candidate tokens that are aligned to a single gold token.
-                gold_i = cand_to_gold[cand_i][0]
+        c2g_single_toks = numpy.where(cand_to_gold.lengths == 1)[0]
-                if gold_to_cand.lengths[heads[gold_i]] == 1:
+
-                    aligned_heads[cand_i] = int(gold_to_cand[heads[gold_i]][0])
+        # Fetch all aligned gold token incides.
-                    aligned_deps[cand_i] = deps[gold_i]
+        if c2g_single_toks.shape == cand_to_gold.lengths.shape:
-        return aligned_heads, aligned_deps
+            # This the most likely case.
+            gold_i = cand_to_gold[:].squeeze()
+        else:
+            gold_i = numpy.vectorize(lambda x: cand_to_gold[int(x)][0])(c2g_single_toks).squeeze()
+
+        # Fetch indices of all gold heads for the aligned gold tokens.
+        heads = numpy.asarray(heads, dtype='i')
+        gold_head_i = heads[gold_i]
+
+        # Select all gold tokens that are heads of the previously selected 
+        # gold tokens (and are aligned to a single candidate token).
+        g2c_len_heads = gold_to_cand.lengths[gold_head_i]
+        g2c_len_heads = numpy.where(g2c_len_heads == 1)[0]
+        g2c_i = numpy.vectorize(lambda x: gold_to_cand[int(x)][0])(gold_head_i[g2c_len_heads]).squeeze()
+
+        # Update head/dep alignments with the above.
+        aligned_heads = numpy.full((self.x.length), None)
+        aligned_heads[c2g_single_toks[g2c_len_heads]] = g2c_i
+
+        deps = numpy.asarray(deps)
+        aligned_deps = numpy.full((self.x.length), None)
+        aligned_deps[c2g_single_toks] = deps[gold_i]
+
+        return aligned_heads.tolist(), aligned_deps.tolist()
 
     def get_aligned_sent_starts(self):
         """Get list of SENT_START attributes aligned to the predicted tokenization.
-        If the reference has not sentence starts, return a list of None values.
+        If the reference does not have sentence starts, return a list of None values.
         """
         if self.y.has_annotation("SENT_START"):
             align = self.alignment.y2x
@@ -519,7 +596,7 @@ def _parse_ner_tags(biluo_or_offsets, vocab, words, spaces):
         else:
             ent_iobs.append(iob_tag.split("-")[0])
             if iob_tag.startswith("I") or iob_tag.startswith("B"):
-                ent_types.append(iob_tag.split("-", 1)[1])
+                ent_types.append(remove_bilu_prefix(iob_tag))
             else:
                 ent_types.append("")
     return ent_iobs, ent_types

spacy/training/iob_utils.py

@@ -1,4 +1,4 @@
-from typing import List, Dict, Tuple, Iterable, Union, Iterator
+from typing import List, Dict, Tuple, Iterable, Union, Iterator, cast
 import warnings
 
 from ..errors import Errors, Warnings
@@ -218,6 +218,14 @@ def tags_to_entities(tags: Iterable[str]) -> List[Tuple[str, int, int]]:
     return entities
 
 
+def split_bilu_label(label: str) -> Tuple[str, str]:
+    return cast(Tuple[str, str], label.split("-", 1))
+
+
+def remove_bilu_prefix(label: str) -> str:
+    return label.split("-", 1)[1]
+
+
 # Fallbacks to make backwards-compat easier
 offsets_from_biluo_tags = biluo_tags_to_offsets
 spans_from_biluo_tags = biluo_tags_to_spans

spacy/util.py

@@ -1,6 +1,6 @@
 from typing import List, Mapping, NoReturn, Union, Dict, Any, Set, cast
 from typing import Optional, Iterable, Callable, Tuple, Type
-from typing import Iterator, Type, Pattern, Generator, TYPE_CHECKING
+from typing import Iterator, Pattern, Generator, TYPE_CHECKING
 from types import ModuleType
 import os
 import importlib
@@ -12,7 +12,6 @@ from thinc.api import NumpyOps, get_current_ops, Adam, Config, Optimizer
 from thinc.api import ConfigValidationError, Model
 import functools
 import itertools
-import numpy.random
 import numpy
 import srsly
 import catalogue
@@ -400,6 +399,7 @@ def load_model(
     *,
     vocab: Union["Vocab", bool] = True,
     disable: Iterable[str] = SimpleFrozenList(),
+    enable: Iterable[str] = SimpleFrozenList(),
     exclude: Iterable[str] = SimpleFrozenList(),
     config: Union[Dict[str, Any], Config] = SimpleFrozenDict(),
 ) -> "Language":
@@ -409,11 +409,19 @@ def load_model(
     vocab (Vocab / True): Optional vocab to pass in on initialization. If True,
         a new Vocab object will be created.
     disable (Iterable[str]): Names of pipeline components to disable.
+    enable (Iterable[str]): Names of pipeline components to enable. All others will be disabled.
+    exclude (Iterable[str]):  Names of pipeline components to exclude.
     config (Dict[str, Any] / Config): Config overrides as nested dict or dict
         keyed by section values in dot notation.
     RETURNS (Language): The loaded nlp object.
     """
-    kwargs = {"vocab": vocab, "disable": disable, "exclude": exclude, "config": config}
+    kwargs = {
+        "vocab": vocab,
+        "disable": disable,
+        "enable": enable,
+        "exclude": exclude,
+        "config": config,
+    }
     if isinstance(name, str):  # name or string path
         if name.startswith("blank:"):  # shortcut for blank model
             return get_lang_class(name.replace("blank:", ""))()
@@ -433,6 +441,7 @@ def load_model_from_package(
     *,
     vocab: Union["Vocab", bool] = True,
     disable: Iterable[str] = SimpleFrozenList(),
+    enable: Iterable[str] = SimpleFrozenList(),
     exclude: Iterable[str] = SimpleFrozenList(),
     config: Union[Dict[str, Any], Config] = SimpleFrozenDict(),
 ) -> "Language":
@@ -444,6 +453,8 @@ def load_model_from_package(
     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.
     config (Dict[str, Any] / Config): Config overrides as nested dict or dict
@@ -451,7 +462,7 @@ def load_model_from_package(
     RETURNS (Language): The loaded nlp object.
     """
     cls = importlib.import_module(name)
-    return cls.load(vocab=vocab, disable=disable, exclude=exclude, config=config)  # type: ignore[attr-defined]
+    return cls.load(vocab=vocab, disable=disable, enable=enable, exclude=exclude, config=config)  # type: ignore[attr-defined]
 
 
 def load_model_from_path(
@@ -460,6 +471,7 @@ def load_model_from_path(
     meta: Optional[Dict[str, Any]] = None,
     vocab: Union["Vocab", bool] = True,
     disable: Iterable[str] = SimpleFrozenList(),
+    enable: Iterable[str] = SimpleFrozenList(),
     exclude: Iterable[str] = SimpleFrozenList(),
     config: Union[Dict[str, Any], Config] = SimpleFrozenDict(),
 ) -> "Language":
@@ -473,6 +485,8 @@ def load_model_from_path(
     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.
     config (Dict[str, Any] / Config): Config overrides as nested dict or dict
@@ -487,7 +501,12 @@ def load_model_from_path(
     overrides = dict_to_dot(config)
     config = load_config(config_path, overrides=overrides)
     nlp = load_model_from_config(
-        config, vocab=vocab, disable=disable, exclude=exclude, meta=meta
+        config,
+        vocab=vocab,
+        disable=disable,
+        enable=enable,
+        exclude=exclude,
+        meta=meta,
     )
     return nlp.from_disk(model_path, exclude=exclude, overrides=overrides)
 
@@ -498,6 +517,7 @@ def load_model_from_config(
     meta: Dict[str, Any] = SimpleFrozenDict(),
     vocab: Union["Vocab", bool] = True,
     disable: Iterable[str] = SimpleFrozenList(),
+    enable: Iterable[str] = SimpleFrozenList(),
     exclude: Iterable[str] = SimpleFrozenList(),
     auto_fill: bool = False,
     validate: bool = True,
@@ -512,6 +532,8 @@ def load_model_from_config(
     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.
     auto_fill (bool): Whether to auto-fill config with missing defaults.
@@ -530,6 +552,7 @@ def load_model_from_config(
         config,
         vocab=vocab,
         disable=disable,
+        enable=enable,
         exclude=exclude,
         auto_fill=auto_fill,
         validate=validate,
@@ -594,6 +617,7 @@ def load_model_from_init_py(
     *,
     vocab: Union["Vocab", bool] = True,
     disable: Iterable[str] = SimpleFrozenList(),
+    enable: Iterable[str] = SimpleFrozenList(),
     exclude: Iterable[str] = SimpleFrozenList(),
     config: Union[Dict[str, Any], Config] = SimpleFrozenDict(),
 ) -> "Language":
@@ -605,6 +629,8 @@ def load_model_from_init_py(
     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.
     config (Dict[str, Any] / Config): Config overrides as nested dict or dict
@@ -622,6 +648,7 @@ def load_model_from_init_py(
         vocab=vocab,
         meta=meta,
         disable=disable,
+        enable=enable,
         exclude=exclude,
         config=config,
     )
@@ -1242,6 +1269,15 @@ def filter_spans(spans: Iterable["Span"]) -> List["Span"]:
     return result
 
 
+def filter_chain_spans(*spans: Iterable["Span"]) -> List["Span"]:
+    return filter_spans(itertools.chain(*spans))
+
+
+@registry.misc("spacy.first_longest_spans_filter.v1")
+def make_first_longest_spans_filter():
+    return filter_chain_spans
+
+
 def to_bytes(getters: Dict[str, Callable[[], bytes]], exclude: Iterable[str]) -> bytes:
     return srsly.msgpack_dumps(to_dict(getters, exclude))
 
@@ -1680,3 +1716,10 @@ def packages_distributions() -> Dict[str, List[str]]:
         for pkg in (dist.read_text("top_level.txt") or "").split():
             pkg_to_dist[pkg].append(dist.metadata["Name"])
     return dict(pkg_to_dist)
+
+
+def all_equal(iterable):
+    """Return True if all the elements are equal to each other
+    (or if the input is an empty sequence), False otherwise."""
+    g = itertools.groupby(iterable)
+    return next(g, True) and not next(g, False)

spacy/vectors.pyx

@@ -339,7 +339,7 @@ cdef class Vectors:
             return self.key2row.get(key, -1)
         elif keys is not None:
             keys = [get_string_id(key) for key in keys]
-            rows = [self.key2row.get(key, -1.) for key in keys]
+            rows = [self.key2row.get(key, -1) for key in keys]
             return xp.asarray(rows, dtype="i")
         else:
             row2key = {row: key for key, row in self.key2row.items()}

website/docs/api/architectures.md

@@ -587,7 +587,7 @@ consists of either two or three subnetworks:
   run once for each batch.
 - **lower**: Construct a feature-specific vector for each `(token, feature)`
   pair. This is also run once for each batch. Constructing the state
-  representation is then simply a matter of summing the component features and
+  representation is then a matter of summing the component features and
   applying the non-linearity.
 - **upper** (optional): A feed-forward network that predicts scores from the
   state representation. If not present, the output from the lower model is used
@@ -628,7 +628,7 @@ same signature, but the `use_upper` argument was `True` by default.
 > ```
 
 Build a tagger model, using a provided token-to-vector component. The tagger
-model simply adds a linear layer with softmax activation to predict scores given
+model adds a linear layer with softmax activation to predict scores given
 the token vectors.
 
 | Name        | Description                                                                                |
@@ -920,7 +920,7 @@ A function that reads an existing `KnowledgeBase` from file.
 A function that takes as input a [`KnowledgeBase`](/api/kb) and a
 [`Span`](/api/span) object denoting a named entity, and returns a list of
 plausible [`Candidate`](/api/kb/#candidate) objects. The default
-`CandidateGenerator` simply uses the text of a mention to find its potential
+`CandidateGenerator` uses the text of a mention to find its potential
 aliases in the `KnowledgeBase`. Note that this function is case-dependent.
 
 ## Coreference Architectures

website/docs/api/attributes.md

@@ -0,0 +1,78 @@
+---
+title: Attributes
+teaser: Token attributes
+source: spacy/attrs.pyx
+---
+
+[Token](/api/token) attributes are specified using internal IDs in many places
+including:
+
+- [`Matcher` patterns](/api/matcher#patterns),
+- [`Doc.to_array`](/api/doc#to_array) and
+  [`Doc.from_array`](/api/doc#from_array)
+- [`Doc.has_annotation`](/api/doc#has_annotation)
+- [`MultiHashEmbed`](/api/architectures#MultiHashEmbed) Tok2Vec architecture
+  `attrs`
+
+> ```python
+> import spacy
+> from spacy.attrs import DEP
+>
+> nlp = spacy.blank("en")
+> doc = nlp("There are many attributes.")
+>
+> # DEP always has the same internal value
+> assert DEP == 76
+>
+> # "DEP" is automatically converted to DEP
+> assert DEP == nlp.vocab.strings["DEP"]
+> assert doc.has_annotation(DEP) == doc.has_annotation("DEP")
+>
+> # look up IDs in spacy.attrs.IDS
+> from spacy.attrs import IDS
+> assert IDS["DEP"] == DEP
+> ```
+
+All methods automatically convert between the string version of an ID (`"DEP"`)
+and the internal integer symbols (`DEP`). The internal IDs can be imported from
+`spacy.attrs` or retrieved from the [`StringStore`](/api/stringstore). A map
+from string attribute names to internal attribute IDs is stored in
+`spacy.attrs.IDS`.
+
+The corresponding [`Token` object attributes](/api/token#attributes) can be
+accessed using the same names in lowercase, e.g. `token.orth` or `token.length`.
+For attributes that represent string values, the internal integer ID is
+accessed as `Token.attr`, e.g. `token.dep`, while the string value can be
+retrieved by appending `_` as in `token.dep_`.
+
+
+| Attribute    | Description                                                                                                                                                   |
+| ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `DEP`        | The token's dependency label. ~~str~~                                                                                                                         |
+| `ENT_ID`     | The token's entity ID (`ent_id`). ~~str~~                                                                                                                     |
+| `ENT_IOB`    | The IOB part of the token's entity tag. Uses custom integer vaues rather than the string store: unset is `0`, `I` is `1`, `O` is `2`, and `B` is `3`. ~~str~~ |
+| `ENT_KB_ID`  | The token's entity knowledge base ID. ~~str~~                                                                                                                 |
+| `ENT_TYPE`   | The token's entity label. ~~str~~                                                                                                                             |
+| `IS_ALPHA`   | Token text consists of alphabetic characters. ~~bool~~                                                                                                        |
+| `IS_ASCII`   | Token text consists of ASCII characters. ~~bool~~                                                                                                             |
+| `IS_DIGIT`   | Token text consists of digits. ~~bool~~                                                                                                                       |
+| `IS_LOWER`   | Token text is in lowercase. ~~bool~~                                                                                                                          |
+| `IS_PUNCT`   | Token is punctuation. ~~bool~~                                                                                                                                |
+| `IS_SPACE`   | Token is whitespace. ~~bool~~                                                                                                                                 |
+| `IS_STOP`    | Token is a stop word. ~~bool~~                                                                                                                                |
+| `IS_TITLE`   | Token text is in titlecase. ~~bool~~                                                                                                                          |
+| `IS_UPPER`   | Token text is in uppercase. ~~bool~~                                                                                                                          |
+| `LEMMA`      | The token's lemma. ~~str~~                                                                                                                                    |
+| `LENGTH`     | The length of the token text. ~~int~~                                                                                                                         |
+| `LIKE_EMAIL` | Token text resembles an email address. ~~bool~~                                                                                                               |
+| `LIKE_NUM`   | Token text resembles a number. ~~bool~~                                                                                                                       |
+| `LIKE_URL`   | Token text resembles a URL. ~~bool~~                                                                                                                          |
+| `LOWER`      | The lowercase form of the token text. ~~str~~                                                                                                                 |
+| `MORPH`      | The token's morphological analysis. ~~MorphAnalysis~~                                                                                                         |
+| `NORM`       | The normalized form of the token text. ~~str~~                                                                                                                |
+| `ORTH`       | The exact verbatim text of a token. ~~str~~                                                                                                                   |
+| `POS`        | The token's universal part of speech (UPOS). ~~str~~                                                                                                          |
+| `SENT_START` | Token is start of sentence. ~~bool~~                                                                                                                          |
+| `SHAPE`      | The token's shape. ~~str~~                                                                                                                                    |
+| `SPACY`      | Token has a trailing space. ~~bool~~                                                                                                                          |
+| `TAG`        | The token's fine-grained part of speech. ~~str~~                                                                                                              |

website/docs/api/doc.md

@@ -481,6 +481,45 @@ Deserialize, i.e. import the document contents from a binary string.
 | `exclude`      | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ |
 | **RETURNS**    | The `Doc` object. ~~Doc~~                                                                   |
 
+## Doc.to_json {#to_json tag="method"}
+
+Serializes a document to JSON. Note that this is format differs from the
+deprecated [`JSON training format`](/api/data-formats#json-input).
+
+> #### Example
+>
+> ```python
+> doc = nlp("All we have to decide is what to do with the time that is given us.")
+> assert doc.to_json()["text"] == doc.text
+> ```
+
+| Name         | Description                                                                                                                                                                                                    |
+| ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `underscore` | Optional list of string names of custom `Doc` attributes. Attribute values need to be JSON-serializable. Values will be added to an `"_"` key in the data, e.g. `"_": {"foo": "bar"}`. ~~Optional[List[str]]~~ |
+| **RETURNS**  | The data in JSON format. ~~Dict[str, Any]~~                                                                                                                                                                    |
+
+## Doc.from_json {#from_json tag="method" new="3.3.1"}
+
+Deserializes a document from JSON, i.e. generates a document from the provided
+JSON data as generated by [`Doc.to_json()`](/api/doc#to_json).
+
+> #### Example
+>
+> ```python
+> from spacy.tokens import Doc
+> doc = nlp("All we have to decide is what to do with the time that is given us.")
+> doc_json = doc.to_json()
+> deserialized_doc = Doc(nlp.vocab).from_json(doc_json)
+> assert deserialized_doc.text == doc.text == doc_json["text"]
+> ```
+
+| Name           | Description                                                                                                          |
+| -------------- | -------------------------------------------------------------------------------------------------------------------- |
+| `doc_json`     | The Doc data in JSON format from [`Doc.to_json`](#to_json). ~~Dict[str, Any]~~                                       |
+| _keyword-only_ |                                                                                                                      |
+| `validate`     | Whether to validate the JSON input against the expected schema for detailed debugging. Defaults to `False`. ~~bool~~ |
+| **RETURNS**    | A `Doc` corresponding to the provided JSON. ~~Doc~~                                                                  |
+
 ## Doc.retokenize {#retokenize tag="contextmanager" new="2.1"}
 
 Context manager to handle retokenization of the `Doc`. Modifications to the

website/docs/api/entityruler.md

@@ -290,7 +290,7 @@ Load the pipe from a bytestring. Modifies the object in place and returns it.
 >
 > ```python
 > ruler_bytes = ruler.to_bytes()
-> ruler = nlp.add_pipe("enity_ruler")
+> ruler = nlp.add_pipe("entity_ruler")
 > ruler.from_bytes(ruler_bytes)
 > ```
 

website/docs/api/matcher.md

@@ -113,6 +113,10 @@ string where an integer is expected) or unexpected property names.
 
 Find all token sequences matching the supplied patterns on the `Doc` or `Span`.
 
+Note that if a single label has multiple patterns associated with it, the
+returned matches don't provide a way to tell which pattern was responsible for
+the match.
+
 > #### Example
 >
 > ```python
@@ -131,7 +135,7 @@ Find all token sequences matching the supplied patterns on the `Doc` or `Span`.
 | _keyword-only_                                   |                                                                                                                                                                                                                                                                                                          |
 | `as_spans` <Tag variant="new">3</Tag>            | Instead of tuples, return a list of [`Span`](/api/span) objects of the matches, with the `match_id` assigned as the span label. Defaults to `False`. ~~bool~~                                                                                                                                            |
 | `allow_missing` <Tag variant="new">3</Tag>       | Whether to skip checks for missing annotation for attributes included in patterns. Defaults to `False`. ~~bool~~                                                                                                                                                                                         |
-| `with_alignments` <Tag variant="new">3.0.6</Tag> | Return match alignment information as part of the match tuple as `List[int]` with the same length as the matched span. Each entry denotes the corresponding index of the token pattern. If `as_spans` is set to `True`, this setting is ignored. Defaults to `False`. ~~bool~~                           |
+| `with_alignments` <Tag variant="new">3.0.6</Tag> | Return match alignment information as part of the match tuple as `List[int]` with the same length as the matched span. Each entry denotes the corresponding index of the token in the pattern. If `as_spans` is set to `True`, this setting is ignored. Defaults to `False`. ~~bool~~                    |
 | **RETURNS**                                      | A list of `(match_id, start, end)` tuples, describing the matches. A match tuple describes a span `doc[start:end`]. The `match_id` is the ID of the added match pattern. If `as_spans` is set to `True`, a list of `Span` objects is returned instead. ~~Union[List[Tuple[int, int, int]], List[Span]]~~ |
 
 ## Matcher.\_\_len\_\_ {#len tag="method" new="2"}

website/docs/api/pipeline-functions.md

@@ -7,6 +7,7 @@ menu:
   - ['merge_entities', 'merge_entities']
   - ['merge_subtokens', 'merge_subtokens']
   - ['token_splitter', 'token_splitter']
+  - ['doc_cleaner', 'doc_cleaner']
 ---
 
 ## merge_noun_chunks {#merge_noun_chunks tag="function"}

website/docs/api/span.md

@@ -27,6 +27,7 @@ Create a `Span` object from the slice `doc[start : end]`.
 | `vector`      | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~          |
 | `vector_norm` | The L2 norm of the document's vector representation. ~~float~~                          |
 | `kb_id`       | A knowledge base ID to attach to the span, e.g. for named entities. ~~Union[str, int]~~ |
+| `span_id`     | An ID to associate with the span. ~~Union[str, int]~~                                   |
 
 ## Span.\_\_getitem\_\_ {#getitem tag="method"}
 
@@ -560,7 +561,9 @@ overlaps with will be returned.
 | `lemma_`                                | The span's lemma. Equivalent to `"".join(token.text_with_ws for token in span)`. ~~str~~                                      |
 | `kb_id`                                 | The hash value of the knowledge base ID referred to by the span. ~~int~~                                                      |
 | `kb_id_`                                | The knowledge base ID referred to by the span. ~~str~~                                                                        |
-| `ent_id`                                | The hash value of the named entity the token is an instance of. ~~int~~                                                       |
+| `ent_id`                                | The hash value of the named entity the root token is an instance of. ~~int~~                                                  |
-| `ent_id_`                               | The string ID of the named entity the token is an instance of. ~~str~~                                                        |
+| `ent_id_`                               | The string ID of the named entity the root token is an instance of. ~~str~~                                                   |
+| `id`                                    | The hash value of the span's ID. ~~int~~                                                                                      |
+| `id_`                                   | The span's ID. ~~str~~                                                                                                        |
 | `sentiment`                             | A scalar value indicating the positivity or negativity of the span. ~~float~~                                                 |
 | `_`                                     | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~ |

website/docs/api/spanruler.md

@@ -0,0 +1,351 @@
+---
+title: SpanRuler
+tag: class
+source: spacy/pipeline/span_ruler.py
+new: 3.3
+teaser: 'Pipeline component for rule-based span and named entity recognition'
+api_string_name: span_ruler
+api_trainable: false
+---
+
+The span ruler lets you add spans to [`Doc.spans`](/api/doc#spans) and/or
+[`Doc.ents`](/api/doc#ents) using token-based rules or exact phrase matches. For
+usage examples, see the docs on
+[rule-based span matching](/usage/rule-based-matching#spanruler).
+
+## Assigned Attributes {#assigned-attributes}
+
+Matches will be saved to `Doc.spans[spans_key]` as a
+[`SpanGroup`](/api/spangroup) and/or to `Doc.ents`, where the annotation is
+saved in the `Token.ent_type` and `Token.ent_iob` fields.
+
+| Location               | Value                                                             |
+| ---------------------- | ----------------------------------------------------------------- |
+| `Doc.spans[spans_key]` | The annotated spans. ~~SpanGroup~~                                |
+| `Doc.ents`             | The annotated spans. ~~Tuple[Span]~~                              |
+| `Token.ent_iob`        | An enum encoding of the IOB part of the named entity tag. ~~int~~ |
+| `Token.ent_iob_`       | The IOB part of the named entity tag. ~~str~~                     |
+| `Token.ent_type`       | The label part of the named entity tag (hash). ~~int~~            |
+| `Token.ent_type_`      | The label part of the named entity tag. ~~str~~                   |
+
+## Config and implementation {#config}
+
+The default config is defined by the pipeline component factory and describes
+how the component should be configured. You can override its settings via the
+`config` argument on [`nlp.add_pipe`](/api/language#add_pipe) or in your
+[`config.cfg`](/usage/training#config).
+
+> #### Example
+>
+> ```python
+> config = {
+>    "spans_key": "my_spans",
+>    "validate": True,
+>    "overwrite": False,
+> }
+> nlp.add_pipe("span_ruler", config=config)
+> ```
+
+| Setting               | Description                                                                                                                                                                             |
+| --------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `spans_key`           | The spans key to save the spans under. If `None`, no spans are saved. Defaults to `"ruler"`. ~~Optional[str]~~                                                                          |
+| `spans_filter`        | The optional method to filter spans before they are assigned to doc.spans. Defaults to `None`. ~~Optional[Callable[[Iterable[Span], Iterable[Span]], List[Span]]]~~                     |
+| `annotate_ents`       | Whether to save spans to doc.ents. Defaults to `False`. ~~bool~~                                                                                                                        |
+| `ents_filter`         | The method to filter spans before they are assigned to doc.ents. Defaults to `util.filter_chain_spans`. ~~Callable[[Iterable[Span], Iterable[Span]], List[Span]]~~                      |
+| `phrase_matcher_attr` | Token attribute to match on, passed to the internal PhraseMatcher as `attr`. Defaults to `None`. ~~Optional[Union[int, str]]~~                                                          |
+| `validate`            | Whether patterns should be validated, passed to Matcher and PhraseMatcher as `validate`. Defaults to `False`. ~~bool~~                                                                  |
+| `overwrite`           | Whether to remove any existing spans under `Doc.spans[spans key]` if `spans_key` is set, or to remove any ents under `Doc.ents` if `annotate_ents` is set. Defaults to `True`. ~~bool~~ |
+| `scorer`              | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for `Doc.spans[spans_key]` with overlapping spans allowed. ~~Optional[Callable]~~                       |
+
+```python
+%%GITHUB_SPACY/spacy/pipeline/span_ruler.py
+```
+
+## SpanRuler.\_\_init\_\_ {#init tag="method"}
+
+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"}`.
+
+> #### Example
+>
+> ```python
+> # Construction via add_pipe
+> ruler = nlp.add_pipe("span_ruler")
+>
+> # Construction from class
+> from spacy.pipeline import SpanRuler
+> ruler = SpanRuler(nlp, overwrite=True)
+> ```
+
+| Name                  | Description                                                                                                                                                                                                                         |
+| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `nlp`                 | The shared nlp object to pass the vocab to the matchers and process phrase patterns. ~~Language~~                                                                                                                                   |
+| `name`                | 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. ~~str~~ |
+| _keyword-only_        |                                                                                                                                                                                                                                     |
+| `spans_key`           | The spans key to save the spans under. If `None`, no spans are saved. Defaults to `"ruler"`. ~~Optional[str]~~                                                                                                                      |
+| `spans_filter`        | The optional method to filter spans before they are assigned to doc.spans. Defaults to `None`. ~~Optional[Callable[[Iterable[Span], Iterable[Span]], List[Span]]]~~                                                                 |
+| `annotate_ents`       | Whether to save spans to doc.ents. Defaults to `False`. ~~bool~~                                                                                                                                                                    |
+| `ents_filter`         | The method to filter spans before they are assigned to doc.ents. Defaults to `util.filter_chain_spans`. ~~Callable[[Iterable[Span], Iterable[Span]], List[Span]]~~                                                                  |
+| `phrase_matcher_attr` | Token attribute to match on, passed to the internal PhraseMatcher as `attr`. Defaults to `None`. ~~Optional[Union[int, str]]~~                                                                                                      |
+| `validate`            | Whether patterns should be validated, passed to Matcher and PhraseMatcher as `validate`. Defaults to `False`. ~~bool~~                                                                                                              |
+| `overwrite`           | Whether to remove any existing spans under `Doc.spans[spans key]` if `spans_key` is set, or to remove any ents under `Doc.ents` if `annotate_ents` is set. Defaults to `True`. ~~bool~~                                             |
+| `scorer`              | The scoring method. Defaults to [`Scorer.score_spans`](/api/scorer#score_spans) for `Doc.spans[spans_key]` with overlapping spans allowed. ~~Optional[Callable]~~                                                                   |
+
+## SpanRuler.initialize {#initialize tag="method"}
+
+Initialize the component with data and used before training to load in rules
+from a [pattern file](/usage/rule-based-matching/#spanruler-files). This method
+is typically called by [`Language.initialize`](/api/language#initialize) and
+lets you customize arguments it receives via the
+[`[initialize.components]`](/api/data-formats#config-initialize) block in the
+config. Any existing patterns are removed on initialization.
+
+> #### Example
+>
+> ```python
+> span_ruler = nlp.add_pipe("span_ruler")
+> span_ruler.initialize(lambda: [], nlp=nlp, patterns=patterns)
+> ```
+>
+> ```ini
+> ### config.cfg
+> [initialize.components.span_ruler]
+>
+> [initialize.components.span_ruler.patterns]
+> @readers = "srsly.read_jsonl.v1"
+> path = "corpus/span_ruler_patterns.jsonl
+> ```
+
+| Name           | Description                                                                                                                                                        |
+| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `get_examples` | Function that returns gold-standard annotations in the form of [`Example`](/api/example) objects. Not used by the `SpanRuler`. ~~Callable[[], Iterable[Example]]~~ |
+| _keyword-only_ |                                                                                                                                                                    |
+| `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                               |
+| `patterns`     | The list of patterns. Defaults to `None`. ~~Optional[Sequence[Dict[str, Union[str, List[Dict[str, Any]]]]]]~~                                                      |
+
+## SpanRuler.\_\len\_\_ {#len tag="method"}
+
+The number of all patterns added to the span ruler.
+
+> #### Example
+>
+> ```python
+> ruler = nlp.add_pipe("span_ruler")
+> assert len(ruler) == 0
+> ruler.add_patterns([{"label": "ORG", "pattern": "Apple"}])
+> assert len(ruler) == 1
+> ```
+
+| Name        | Description                     |
+| ----------- | ------------------------------- |
+| **RETURNS** | The number of patterns. ~~int~~ |
+
+## SpanRuler.\_\_contains\_\_ {#contains tag="method"}
+
+Whether a label is present in the patterns.
+
+> #### Example
+>
+> ```python
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.add_patterns([{"label": "ORG", "pattern": "Apple"}])
+> assert "ORG" in ruler
+> assert not "PERSON" in ruler
+> ```
+
+| Name        | Description                                         |
+| ----------- | --------------------------------------------------- |
+| `label`     | The label to check. ~~str~~                         |
+| **RETURNS** | Whether the span ruler contains the label. ~~bool~~ |
+
+## SpanRuler.\_\_call\_\_ {#call tag="method"}
+
+Find matches in the `Doc` and add them to `doc.spans[span_key]` and/or
+`doc.ents`. Typically, this happens automatically after the component has been
+added to the pipeline using [`nlp.add_pipe`](/api/language#add_pipe). If the
+span ruler was initialized with `overwrite=True`, existing spans and entities
+will be removed.
+
+> #### Example
+>
+> ```python
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.add_patterns([{"label": "ORG", "pattern": "Apple"}])
+>
+> doc = nlp("A text about Apple.")
+> spans = [(span.text, span.label_) for span in doc.spans["ruler"]]
+> assert spans == [("Apple", "ORG")]
+> ```
+
+| Name        | Description                                                          |
+| ----------- | -------------------------------------------------------------------- |
+| `doc`       | The `Doc` object to process, e.g. the `Doc` in the pipeline. ~~Doc~~ |
+| **RETURNS** | The modified `Doc` with added spans/entities. ~~Doc~~                |
+
+## SpanRuler.add_patterns {#add_patterns tag="method"}
+
+Add patterns to the span ruler. A pattern can either be a token pattern (list of
+dicts) or a phrase pattern (string). For more details, see the usage guide on
+[rule-based matching](/usage/rule-based-matching).
+
+> #### Example
+>
+> ```python
+> patterns = [
+>     {"label": "ORG", "pattern": "Apple"},
+>     {"label": "GPE", "pattern": [{"lower": "san"}, {"lower": "francisco"}]}
+> ]
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.add_patterns(patterns)
+> ```
+
+| Name       | Description                                                      |
+| ---------- | ---------------------------------------------------------------- |
+| `patterns` | The patterns to add. ~~List[Dict[str, Union[str, List[dict]]]]~~ |
+
+## SpanRuler.remove {#remove tag="method"}
+
+Remove patterns by label from the span ruler. A `ValueError` is raised if the
+label does not exist in any patterns.
+
+> #### Example
+>
+> ```python
+> patterns = [{"label": "ORG", "pattern": "Apple", "id": "apple"}]
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.add_patterns(patterns)
+> ruler.remove("ORG")
+> ```
+
+| Name    | Description                            |
+| ------- | -------------------------------------- |
+| `label` | The label of the pattern rule. ~~str~~ |
+
+## SpanRuler.remove_by_id {#remove_by_id tag="method"}
+
+Remove patterns by ID from the span ruler. A `ValueError` is raised if the ID
+does not exist in any patterns.
+
+> #### Example
+>
+> ```python
+> patterns = [{"label": "ORG", "pattern": "Apple", "id": "apple"}]
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.add_patterns(patterns)
+> ruler.remove_by_id("apple")
+> ```
+
+| Name         | Description                         |
+| ------------ | ----------------------------------- |
+| `pattern_id` | The ID of the pattern rule. ~~str~~ |
+
+## SpanRuler.clear {#clear tag="method"}
+
+Remove all patterns the span ruler.
+
+> #### Example
+>
+> ```python
+> patterns = [{"label": "ORG", "pattern": "Apple", "id": "apple"}]
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.add_patterns(patterns)
+> ruler.clear()
+> ```
+
+## SpanRuler.to_disk {#to_disk tag="method"}
+
+Save the span ruler patterns to a directory. The patterns will be saved as
+newline-delimited JSON (JSONL).
+
+> #### Example
+>
+> ```python
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.to_disk("/path/to/span_ruler")
+> ```
+
+| Name   | Description                                                                                                                                |
+| ------ | ------------------------------------------------------------------------------------------------------------------------------------------ |
+| `path` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
+
+## SpanRuler.from_disk {#from_disk tag="method"}
+
+Load the span ruler from a path.
+
+> #### Example
+>
+> ```python
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.from_disk("/path/to/span_ruler")
+> ```
+
+| Name        | Description                                                                                     |
+| ----------- | ----------------------------------------------------------------------------------------------- |
+| `path`      | A path to a directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ |
+| **RETURNS** | The modified `SpanRuler` object. ~~SpanRuler~~                                                  |
+
+## SpanRuler.to_bytes {#to_bytes tag="method"}
+
+Serialize the span ruler to a bytestring.
+
+> #### Example
+>
+> ```python
+> ruler = nlp.add_pipe("span_ruler")
+> ruler_bytes = ruler.to_bytes()
+> ```
+
+| Name        | Description                        |
+| ----------- | ---------------------------------- |
+| **RETURNS** | The serialized patterns. ~~bytes~~ |
+
+## SpanRuler.from_bytes {#from_bytes tag="method"}
+
+Load the pipe from a bytestring. Modifies the object in place and returns it.
+
+> #### Example
+>
+> ```python
+> ruler_bytes = ruler.to_bytes()
+> ruler = nlp.add_pipe("span_ruler")
+> ruler.from_bytes(ruler_bytes)
+> ```
+
+| Name         | Description                                    |
+| ------------ | ---------------------------------------------- |
+| `bytes_data` | The bytestring to load. ~~bytes~~              |
+| **RETURNS**  | The modified `SpanRuler` object. ~~SpanRuler~~ |
+
+## SpanRuler.labels {#labels tag="property"}
+
+All labels present in the match patterns.
+
+| Name        | Description                            |
+| ----------- | -------------------------------------- |
+| **RETURNS** | The string labels. ~~Tuple[str, ...]~~ |
+
+## SpanRuler.ids {#ids tag="property"}
+
+All IDs present in the `id` property of the match patterns.
+
+| Name        | Description                         |
+| ----------- | ----------------------------------- |
+| **RETURNS** | The string IDs. ~~Tuple[str, ...]~~ |
+
+## SpanRuler.patterns {#patterns tag="property"}
+
+All patterns that were added to the span ruler.
+
+| Name        | Description                                                                              |
+| ----------- | ---------------------------------------------------------------------------------------- |
+| **RETURNS** | The original patterns, one dictionary per pattern. ~~List[Dict[str, Union[str, dict]]]~~ |
+
+## Attributes {#attributes}
+
+| Name             | Description                                                                      |
+| ---------------- | -------------------------------------------------------------------------------- |
+| `key`            | The spans key that spans are saved under. ~~Optional[str]~~                      |
+| `matcher`        | The underlying matcher used to process token patterns. ~~Matcher~~               |
+| `phrase_matcher` | The underlying phrase matcher used to process phrase patterns. ~~PhraseMatcher~~ |

website/docs/api/stringstore.md

@@ -161,7 +161,7 @@ Load state from a binary string.
 > #### Example
 >
 > ```python
-> fron spacy.strings import StringStore
+> from spacy.strings import StringStore
 > store_bytes = stringstore.to_bytes()
 > new_store = StringStore().from_bytes(store_bytes)
 > ```

website/docs/api/token.md

@@ -221,7 +221,7 @@ dependency tree.
 
 ## Token.ancestors {#ancestors tag="property" model="parser"}
 
-The rightmost token of this token's syntactic descendants.
+A sequence of the token's syntactic ancestors (parents, grandparents, etc).
 
 > #### Example
 >

website/docs/api/top-level.md

@@ -51,6 +51,7 @@ specified separately using the new `exclude` keyword argument.
 | _keyword-only_                       |                                                                                                                                                                                                                                                |
 | `vocab`                              | Optional shared vocab to pass in on initialization. If `True` (default), a new `Vocab` object will be created. ~~Union[Vocab, bool]~~                                                                                                          |
 | `disable`                            | Names of pipeline components to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [nlp.enable_pipe](/api/language#enable_pipe). ~~List[str]~~ |
+| `enable`                             | Names of pipeline components to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled. ~~List[str]~~                                                                                                               |
 | `exclude` <Tag variant="new">3</Tag> | Names of pipeline components to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~List[str]~~                                                                                                           |
 | `config` <Tag variant="new">3</Tag>  | Optional config overrides, either as nested dict or dict keyed by section value in dot notation, e.g. `"components.name.value"`. ~~Union[Dict[str, Any], Config]~~                                                                             |
 | **RETURNS**                          | A `Language` object with the loaded pipeline. ~~Language~~                                                                                                                                                                                     |
@@ -239,7 +240,7 @@ browser. Will run a simple web server.
 | Name      | Description                                                                                                                                                       |
 | --------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `docs`    | Document(s) or span(s) to visualize. ~~Union[Iterable[Union[Doc, Span]], Doc, Span]~~                                                                             |
-| `style`   | Visualization style, `"dep"` or `"ent"`. Defaults to `"dep"`. ~~str~~                                                                                             |
+| `style`   | Visualization style, `"dep"`, `"ent"` or `"span"` <Tag variant="new">3.3</Tag>. Defaults to `"dep"`. ~~str~~                                                                                             |
 | `page`    | Render markup as full HTML page. Defaults to `True`. ~~bool~~                                                                                                     |
 | `minify`  | Minify HTML markup. Defaults to `False`. ~~bool~~                                                                                                                 |
 | `options` | [Visualizer-specific options](#displacy_options), e.g. colors. ~~Dict[str, Any]~~                                                                                 |
@@ -264,7 +265,7 @@ Render a dependency parse tree or named entity visualization.
 | Name        | Description                                                                                                                                                                            |
 | ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `docs`      | Document(s) or span(s) to visualize. ~~Union[Iterable[Union[Doc, Span, dict]], Doc, Span, dict]~~                                                                                      |
-| `style`     | Visualization style, `"dep"` or `"ent"`. Defaults to `"dep"`. ~~str~~                                                                                                                  |
+| `style`     | Visualization style,`"dep"`, `"ent"` or `"span"` <Tag variant="new">3.3</Tag>. Defaults to `"dep"`. ~~str~~                                                                                                                  |
 | `page`      | Render markup as full HTML page. Defaults to `True`. ~~bool~~                                                                                                                          |
 | `minify`    | Minify HTML markup. Defaults to `False`. ~~bool~~                                                                                                                                      |
 | `options`   | [Visualizer-specific options](#displacy_options), e.g. colors. ~~Dict[str, Any]~~                                                                                                      |

website/docs/usage/linguistic-features.md

@@ -1899,7 +1899,7 @@ access to some nice Latin vectors. You can then pass the directory path to
 > ```
 
 ```cli
-$ wget https://s3-us-west-1.amazonaws.com/fasttext-vectors/word-vectors-v2/cc.la.300.vec.gz
+$ wget https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.la.300.vec.gz
 $ python -m spacy init vectors en cc.la.300.vec.gz /tmp/la_vectors_wiki_lg
 ```
 

website/docs/usage/processing-pipelines.md

@@ -362,6 +362,18 @@ nlp = spacy.load("en_core_web_sm", disable=["tagger", "parser"])
 nlp.enable_pipe("tagger")
 ```
 
+In addition to `disable`, `spacy.load()` also accepts `enable`. If `enable` is
+set, all components except for those in `enable` are disabled.
+
+```python
+# Load the complete pipeline, but disable all components except for tok2vec and tagger
+nlp = spacy.load("en_core_web_sm", enable=["tok2vec", "tagger"])
+# Has the same effect, as NER is already not part of enabled set of components
+nlp = spacy.load("en_core_web_sm", enable=["tok2vec", "tagger"], disable=["ner"])
+# Will raise an error, as the sets of enabled and disabled components are conflicting
+nlp = spacy.load("en_core_web_sm", enable=["ner"], disable=["ner"])
+```
+
 <Infobox variant="warning" title="Changed in v3.0">
 
 As of v3.0, the `disable` keyword argument specifies components to load but

website/docs/usage/rule-based-matching.md

@@ -6,6 +6,7 @@ menu:
   - ['Phrase Matcher', 'phrasematcher']
   - ['Dependency Matcher', 'dependencymatcher']
   - ['Entity Ruler', 'entityruler']
+  - ['Span Ruler', 'spanruler']
   - ['Models & Rules', 'models-rules']
 ---
 
@@ -1446,6 +1447,108 @@ with nlp.select_pipes(enable="tagger"):
     ruler.add_patterns(patterns)
 ```
 
+## Rule-based span matching {#spanruler new="3.3.1"}
+
+The [`SpanRuler`](/api/spanruler) is a generalized version of the entity ruler
+that lets you add spans to `doc.spans` or `doc.ents` based on pattern
+dictionaries, which makes it easy to combine rule-based and statistical pipeline
+components.
+
+### Span patterns {#spanruler-patterns}
+
+The [pattern format](#entityruler-patterns) is the same as for the entity ruler:
+
+1. **Phrase patterns** for exact string matches (string).
+
+   ```python
+   {"label": "ORG", "pattern": "Apple"}
+   ```
+
+2. **Token patterns** with one dictionary describing one token (list).
+
+   ```python
+   {"label": "GPE", "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}]}
+   ```
+
+### Using the span ruler {#spanruler-usage}
+
+The [`SpanRuler`](/api/spanruler) is a pipeline component that's typically added
+via [`nlp.add_pipe`](/api/language#add_pipe). When the `nlp` object is called on
+a text, it will find matches in the `doc` and add them as spans to
+`doc.spans["ruler"]`, using the specified pattern label as the entity label.
+Unlike in `doc.ents`, overlapping matches are allowed in `doc.spans`, so no
+filtering is required, but optional filtering and sorting can be applied to the
+spans before they're saved.
+
+```python
+### {executable="true"}
+import spacy
+
+nlp = spacy.blank("en")
+ruler = nlp.add_pipe("span_ruler")
+patterns = [{"label": "ORG", "pattern": "Apple"},
+            {"label": "GPE", "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}]}]
+ruler.add_patterns(patterns)
+
+doc = nlp("Apple is opening its first big office in San Francisco.")
+print([(span.text, span.label_) for span in doc.spans["ruler"]])
+```
+
+The span ruler is designed to integrate with spaCy's existing pipeline
+components and enhance the [SpanCategorizer](/api/spancat) and
+[EntityRecognizer](/api/entityrecognizer). The `overwrite` setting determines
+whether the existing annotation in `doc.spans` or `doc.ents` is preserved.
+Because overlapping entities are not allowed for `doc.ents`, the entities are
+always filtered, using [`util.filter_spans`](/api/top-level#util.filter_spans)
+by default. See the [`SpanRuler` API docs](/api/spanruler) for more information
+about how to customize the sorting and filtering of matched spans.
+
+```python
+### {executable="true"}
+import spacy
+
+nlp = spacy.load("en_core_web_sm")
+# only annotate doc.ents, not doc.spans
+config = {"spans_key": None, "annotate_ents": True, "overwrite": False}
+ruler = nlp.add_pipe("span_ruler", config=config)
+patterns = [{"label": "ORG", "pattern": "MyCorp Inc."}]
+ruler.add_patterns(patterns)
+
+doc = nlp("MyCorp Inc. is a company in the U.S.")
+print([(ent.text, ent.label_) for ent in doc.ents])
+```
+
+### Using pattern files {#spanruler-files}
+
+You can save patterns in a JSONL file (newline-delimited JSON) to load with
+[`SpanRuler.initialize`](/api/spanruler#initialize) or
+[`SpanRuler.add_patterns`](/api/spanruler#add_patterns).
+
+```json
+### patterns.jsonl
+{"label": "ORG", "pattern": "Apple"}
+{"label": "GPE", "pattern": [{"LOWER": "san"}, {"LOWER": "francisco"}]}
+```
+
+```python
+import srsly
+
+patterns = srsly.read_jsonl("patterns.jsonl")
+ruler = nlp.add_pipe("span_ruler")
+ruler.add_patterns(patterns)
+```
+
+<Infobox title="Important note" variant="warning">
+
+Unlike the entity ruler, the span ruler cannot load patterns on initialization
+with `SpanRuler(patterns=patterns)` or directly from a JSONL file path with
+`SpanRuler.from_disk(jsonl_path)`. Patterns should be loaded from the JSONL file
+separately and then added through
+[`SpanRuler.initialize`](/api/spanruler#initialize]) or
+[`SpanRuler.add_patterns`](/api/spanruler#add_patterns) as shown above.
+
+</Infobox>
+
 ## Combining models and rules {#models-rules}
 
 You can combine statistical and rule-based components in a variety of ways.

website/docs/usage/saving-loading.md

@@ -203,11 +203,14 @@ the data to and from a JSON file.
 
 ```python
 ### {highlight="16-23,25-30"}
+import json
+from spacy import Language
 from spacy.util import ensure_path
 
 @Language.factory("my_component")
 class CustomComponent:
-    def __init__(self):
+    def __init__(self, nlp: Language, name: str = "my_component"):
+        self.name = name
         self.data = []
 
     def __call__(self, doc):
@@ -231,7 +234,7 @@ class CustomComponent:
         # This will receive the directory path + /my_component
         data_path = path / "data.json"
         with data_path.open("r", encoding="utf8") as f:
-            self.data = json.loads(f)
+            self.data = json.load(f)
         return self
 ```
 

website/meta/sidebars.json

@@ -103,6 +103,7 @@
                     { "text": "SentenceRecognizer", "url": "/api/sentencerecognizer" },
                     { "text": "Sentencizer", "url": "/api/sentencizer" },
                     { "text": "SpanCategorizer", "url": "/api/spancategorizer" },
+                    { "text": "SpanRuler", "url": "/api/spanruler" },
                     { "text": "Tagger", "url": "/api/tagger" },
                     { "text": "TextCategorizer", "url": "/api/textcategorizer" },
                     { "text": "Tok2Vec", "url": "/api/tok2vec" },
@@ -123,6 +124,7 @@
             {
                 "label": "Other",
                 "items": [
+                    { "text": "Attributes", "url": "/api/attributes" },
                     { "text": "Corpus", "url": "/api/corpus" },
                     { "text": "KnowledgeBase", "url": "/api/kb" },
                     { "text": "Lookups", "url": "/api/lookups" },

website/meta/universe.json

@@ -1,5 +1,77 @@
 {
     "resources": [
+        {
+            "id": "spacyfishing",
+            "title": "spaCy fishing",
+            "slogan": "Named entity disambiguation and linking on Wikidata in spaCy with Entity-Fishing.",
+            "description": "A spaCy wrapper of Entity-Fishing for named entity disambiguation and linking against a Wikidata knowledge base.",
+            "github": "Lucaterre/spacyfishing",
+            "pip": "spacyfishing",
+            "code_example": [
+                "import spacy",
+                "text = 'Victor Hugo and Honoré de Balzac are French writers who lived in Paris.'",
+                "nlp = spacy.load('en_core_web_sm')",
+                "nlp.add_pipe('entityfishing')",
+                "doc = nlp(text)",
+                "for span in doc.ents:",
+                "    print((ent.text, ent.label_, ent._.kb_qid, ent._.url_wikidata, ent._.nerd_score))",
+                "# ('Victor Hugo', 'PERSON', 'Q535', 'https://www.wikidata.org/wiki/Q535', 0.972)",
+                "# ('Honoré de Balzac', 'PERSON', 'Q9711', 'https://www.wikidata.org/wiki/Q9711', 0.9724)",
+                "# ('French', 'NORP', 'Q121842', 'https://www.wikidata.org/wiki/Q121842', 0.3739)",
+                "# ('Paris', 'GPE', 'Q90', 'https://www.wikidata.org/wiki/Q90', 0.5652)",
+                "## Set parameter `extra_info` to `True` and check also span._.description, span._.src_description, span._.normal_term, span._.other_ids"
+            ],
+            "category": ["models", "pipeline"],
+            "tags": ["NER", "NEL"],
+            "author": "Lucas Terriel",
+            "author_links": {
+                "twitter": "TerreLuca",
+                "github": "Lucaterre"
+            }
+        },
+        {
+            "id": "aim-spacy",
+            "title": "Aim-spaCy",
+            "slogan": "Aim-spaCy is an Aim-based spaCy experiment tracker.",
+            "description": "Aim-spaCy helps to easily collect, store and explore training logs for spaCy, including: hyper-parameters, metrics and displaCy visualizations",
+            "github": "aimhubio/aim-spacy",
+            "pip": "aim-spacy",
+            "code_example": [
+                "https://github.com/aimhubio/aim-spacy/tree/master/examples"
+            ],
+            "code_language": "python",
+            "url": "https://aimstack.io/spacy",
+            "thumb": "https://user-images.githubusercontent.com/13848158/172912427-ee9327ea-3cd8-47fa-8427-6c0d36cd831f.png",
+            "image": "https://user-images.githubusercontent.com/13848158/136364717-0939222c-55b6-44f0-ad32-d9ab749546e4.png",
+            "author": "AimStack",
+            "author_links": {
+                "twitter": "aimstackio",
+                "github": "aimhubio",
+                "website": "https://aimstack.io"
+            },
+            "category": ["visualizers"],
+            "tags": ["experiment-tracking", "visualization"]
+        },
+        {
+            "id": "spacy-report",
+            "title": "spacy-report",
+            "slogan": "Generates interactive reports for spaCy models.",
+            "description": "The goal of spacy-report is to offer static reports for spaCy models that help users make better decisions on how the models can be used.",
+            "github": "koaning/spacy-report",
+            "pip": "spacy-report",
+            "thumb": "https://github.com/koaning/spacy-report/raw/main/icon.png",
+            "image": "https://raw.githubusercontent.com/koaning/spacy-report/main/gif.gif",
+            "code_example": [
+                "python -m spacy report textcat training/model-best/ corpus/train.spacy corpus/dev.spacy"
+            ],
+            "category": ["visualizers", "research"],
+            "author": "Vincent D. Warmerdam",
+            "author_links": {
+                "twitter": "fishnets88",
+                "github": "koaning",
+                "website": "https://koaning.io"
+            }
+        },
         {
             "id": "scrubadub_spacy",
             "title": "scrubadub_spacy",
@@ -12,7 +84,7 @@
             "code_language": "python",
             "author": "Leap Beyond",
             "author_links": {
-                "github": "https://github.com/LeapBeyond",
+                "github": "LeapBeyond",
                 "website": "https://leapbeyond.ai"
             },
             "code_example": [
@@ -35,8 +107,8 @@
             "code_language": "python",
             "author": "Peter Baumgartner",
             "author_links": {
-                "twitter" : "https://twitter.com/pmbaumgartner",
+                "twitter" : "pmbaumgartner",
-                "github": "https://github.com/pmbaumgartner",
+                "github": "pmbaumgartner",
                 "website": "https://www.peterbaumgartner.com/"
             },
             "code_example": [
@@ -55,8 +127,8 @@
             "code_language": "python",
             "author": "Explosion",
             "author_links": {
-                "twitter" : "https://twitter.com/explosion_ai",
+                "twitter" : "explosion_ai",
-                "github": "https://github.com/explosion",
+                "github": "explosion",
                 "website": "https://explosion.ai/"
             },
             "code_example": [
@@ -528,8 +600,8 @@
             "code_language": "python",
             "author": "Keith Rozario",
             "author_links": {
-                "twitter" : "https://twitter.com/keithrozario",
+                "twitter" : "keithrozario",
-                "github": "https://github.com/keithrozario",
+                "github": "keithrozario",
                 "website": "https://www.keithrozario.com"
             },
             "code_example": [
@@ -2252,7 +2324,7 @@
             "author": "Daniel Whitenack & Chris Benson",
             "author_links": {
                 "website": "https://changelog.com/practicalai",
-                "twitter": "https://twitter.com/PracticalAIFM"
+                "twitter": "PracticalAIFM"
             },
             "category": ["podcasts"]
         },
@@ -2799,13 +2871,13 @@
             "id": "holmes",
             "title": "Holmes",
             "slogan": "Information extraction from English and German texts based on predicate logic",
-            "github": "msg-systems/holmes-extractor",
+            "github": "explosion/holmes-extractor",
-            "url": "https://github.com/msg-systems/holmes-extractor",
+            "url": "https://github.com/explosion/holmes-extractor",
-            "description": "Holmes is a Python 3 library that supports a number of use cases involving information extraction from English and German texts, including chatbot, structural extraction, topic matching and supervised document classification. There is a [website demonstrating intelligent search based on topic matching](https://holmes-demo.xt.msg.team).",
+            "description": "Holmes is a Python 3 library that supports a number of use cases involving information extraction from English and German texts, including chatbot, structural extraction, topic matching and supervised document classification. There is a [website demonstrating intelligent search based on topic matching](https://demo.holmes.prod.demos.explosion.services).",
             "pip": "holmes-extractor",
-            "category": ["conversational", "standalone"],
+            "category": ["pipeline", "standalone"],
             "tags": ["chatbots", "text-processing"],
-            "thumb": "https://raw.githubusercontent.com/msg-systems/holmes-extractor/master/docs/holmes_thumbnail.png",
+            "thumb": "https://raw.githubusercontent.com/explosion/holmes-extractor/master/docs/holmes_thumbnail.png",
             "code_example": [
                 "import holmes_extractor as holmes",
                 "holmes_manager = holmes.Manager(model='en_core_web_lg')",

website/src/widgets/quickstart-install.js

@@ -24,7 +24,6 @@ const CUDA = {
     '11.3': 'cuda113',
     '11.4': 'cuda114',
     '11.5': 'cuda115',
-    '11.6': 'cuda116',
 }
 const LANG_EXTRAS = ['ja'] // only for languages with models