Merge pull request #1 from explosion/master

Update

.github/azure-steps.yml

@@ -27,7 +27,6 @@ steps:
 
   - script: python -m mypy spacy
     displayName: 'Run mypy'
-    condition: ne(variables['python_version'], '3.10')
 
   - task: DeleteFiles@1
     inputs:
@@ -64,12 +63,12 @@ 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 +92,17 @@ 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 +110,7 @@ steps:
     condition: eq(variables['python_version'], '3.8')
 
   - script: |
-      ${{ parameters.prefix }} python -m pip install thinc-apple-ops
+      ${{ parameters.prefix }} python -m pip install --pre thinc-apple-ops
       ${{ parameters.prefix }} python -m pytest --pyargs spacy
     displayName: "Run CPU tests with thinc-apple-ops"
-    condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.9'))
+    condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.10'))

.github/contributors/Lucaterre.md

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

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

@@ -5,7 +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.dev2,<8.2.0",
+    "thinc>=8.1.0.dev3,<8.2.0",
     "pathy",
     "numpy>=1.15.0",
 ]

requirements.txt

@@ -3,7 +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.dev2,<8.2.0
+thinc>=8.1.0.dev3,<8.2.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.1.0

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.dev2,<8.2.0
+    thinc>=8.1.0.dev3,<8.2.0
 install_requires =
     # Our libraries
     spacy-legacy>=3.0.9,<3.1.0
@@ -46,7 +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.dev2,<8.2.0
+    thinc>=8.1.0.dev3,<8.2.0
     wasabi>=0.9.1,<1.1.0
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
@@ -104,7 +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/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

@@ -462,6 +462,23 @@ def git_sparse_checkout(repo, subpath, dest, branch):
         shutil.move(str(source_path), str(dest))
 
 
+def git_repo_branch_exists(repo: str, branch: str) -> bool:
+    """Uses 'git ls-remote' to check if a repository and branch exists
+
+    repo (str): URL to get repo.
+    branch (str): Branch on repo to check.
+    RETURNS (bool): True if repo:branch exists.
+    """
+    get_git_version()
+    cmd = f"git ls-remote {repo} {branch}"
+    # We might be tempted to use `--exit-code` with `git ls-remote`, but
+    # `run_command` handles the `returncode` for us, so we'll rely on
+    # the fact that stdout returns '' if the requested branch doesn't exist
+    ret = run_command(cmd, capture=True)
+    exists = ret.stdout != ""
+    return exists
+
+
 def get_git_version(
     error: str = "Could not run 'git'. Make sure it's installed and the executable is available.",
 ) -> Tuple[int, int]:

spacy/cli/debug_data.py

@@ -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(

spacy/cli/project/clone.py

@@ -7,11 +7,11 @@ import re
 from ... import about
 from ...util import ensure_path
 from .._util import project_cli, Arg, Opt, COMMAND, PROJECT_FILE
-from .._util import git_checkout, get_git_version
+from .._util import git_checkout, get_git_version, git_repo_branch_exists
 
 DEFAULT_REPO = about.__projects__
 DEFAULT_PROJECTS_BRANCH = about.__projects_branch__
-DEFAULT_BRANCH = "master"
+DEFAULT_BRANCHES = ["main", "master"]
 
 
 @project_cli.command("clone")
@@ -20,7 +20,7 @@ def project_clone_cli(
     name: str = Arg(..., help="The name of the template to clone"),
     dest: Optional[Path] = Arg(None, help="Where to clone the project. Defaults to current working directory", exists=False),
     repo: str = Opt(DEFAULT_REPO, "--repo", "-r", help="The repository to clone from"),
-    branch: Optional[str] = Opt(None, "--branch", "-b", help="The branch to clone from"),
+    branch: Optional[str] = Opt(None, "--branch", "-b", help=f"The branch to clone from. If not provided, will attempt {', '.join(DEFAULT_BRANCHES)}"),
     sparse_checkout: bool = Opt(False, "--sparse", "-S", help="Use sparse Git checkout to only check out and clone the files needed. Requires Git v22.2+.")
     # fmt: on
 ):
@@ -33,9 +33,25 @@ def project_clone_cli(
     """
     if dest is None:
         dest = Path.cwd() / Path(name).parts[-1]
+    if repo == DEFAULT_REPO and branch is None:
+        branch = DEFAULT_PROJECTS_BRANCH
+
     if branch is None:
-        # If it's a user repo, we want to default to other branch
+        for default_branch in DEFAULT_BRANCHES:
-        branch = DEFAULT_PROJECTS_BRANCH if repo == DEFAULT_REPO else DEFAULT_BRANCH
+            if git_repo_branch_exists(repo, default_branch):
+                branch = default_branch
+                break
+        if branch is None:
+            default_branches_msg = ", ".join(f"'{b}'" for b in DEFAULT_BRANCHES)
+            msg.fail(
+                "No branch provided and attempted default "
+                f"branches {default_branches_msg} do not exist.",
+                exits=1,
+            )
+    else:
+        if not git_repo_branch_exists(repo, branch):
+            msg.fail(f"repo: {repo} (branch: {branch}) does not exist.", exits=1)
+    assert isinstance(branch, str)
     project_clone(name, dest, repo=repo, branch=branch, sparse_checkout=sparse_checkout)
 
 
@@ -61,9 +77,9 @@ def project_clone(
     try:
         git_checkout(repo, name, dest, branch=branch, sparse=sparse_checkout)
     except subprocess.CalledProcessError:
-        err = f"Could not clone '{name}' from repo '{repo_name}'"
+        err = f"Could not clone '{name}' from repo '{repo_name}' (branch '{branch}')"
         msg.fail(err, exits=1)
-    msg.good(f"Cloned '{name}' from {repo_name}", project_dir)
+    msg.good(f"Cloned '{name}' from '{repo_name}' (branch '{branch}')", project_dir)
     if not (project_dir / PROJECT_FILE).exists():
         msg.warn(f"No {PROJECT_FILE} found in directory")
     else:

spacy/displacy/render.py

@@ -64,8 +64,11 @@ class SpanRenderer:
         # Set up how the text and labels will be rendered
         self.direction = DEFAULT_DIR
         self.lang = DEFAULT_LANG
+        # These values are in px
         self.top_offset = options.get("top_offset", 40)
-        self.top_offset_step = options.get("top_offset_step", 17)
+        # This is how far under the top offset the span labels appear
+        self.span_label_offset = options.get("span_label_offset", 20)
+        self.offset_step = options.get("top_offset_step", 17)
 
         # Set up which templates will be used
         template = options.get("template")
@@ -161,8 +164,16 @@ class SpanRenderer:
             if entities:
                 slices = self._get_span_slices(token["entities"])
                 starts = self._get_span_starts(token["entities"])
+                total_height = (
+                    self.top_offset
+                    + self.span_label_offset
+                    + (self.offset_step * (len(entities) - 1))
+                )
                 markup += self.span_template.format(
-                    text=token["text"], span_slices=slices, span_starts=starts
+                    text=token["text"],
+                    span_slices=slices,
+                    span_starts=starts,
+                    total_height=total_height,
                 )
             else:
                 markup += escape_html(token["text"] + " ")
@@ -171,7 +182,7 @@ class SpanRenderer:
     def _get_span_slices(self, entities: List[Dict]) -> str:
         """Get the rendered markup of all Span slices"""
         span_slices = []
-        for entity, step in zip(entities, itertools.count(step=self.top_offset_step)):
+        for entity, step in zip(entities, itertools.count(step=self.offset_step)):
             color = self.colors.get(entity["label"].upper(), self.default_color)
             span_slice = self.span_slice_template.format(
                 bg=color, top_offset=self.top_offset + step
@@ -182,7 +193,7 @@ class SpanRenderer:
     def _get_span_starts(self, entities: List[Dict]) -> str:
         """Get the rendered markup of all Span start tokens"""
         span_starts = []
-        for entity, step in zip(entities, itertools.count(step=self.top_offset_step)):
+        for entity, step in zip(entities, itertools.count(step=self.offset_step)):
             color = self.colors.get(entity["label"].upper(), self.default_color)
             span_start = (
                 self.span_start_template.format(

spacy/displacy/templates.py

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

spacy/lang/bg/__init__.py

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

spacy/lang/char_classes.py

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

spacy/lang/punctuation.py

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

spacy/lang/ru/__init__.py

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

spacy/lang/uk/__init__.py

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

spacy/tests/lang/bg/test_tokenizer.py

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

spacy/tests/lang/ru/test_tokenizer.py

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

spacy/tests/lang/uk/test_tokenizer.py

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

spacy/tests/parser/test_ner.py

@@ -158,13 +158,18 @@ def test_issue3209():
 
 
 def test_labels_from_BILUO():
-    """Test that labels are inferred correctly when there's a - in label.
+    """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"]
+    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

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

@@ -679,6 +679,31 @@ def test_projectivize(en_tokenizer):
     assert proj_heads == [3, 2, 3, 3, 3]
     assert nonproj_heads == [3, 2, 3, 3, 2]
 
+    # Test single token documents
+    doc = en_tokenizer("Conrail")
+    heads = [0]
+    deps = ["dep"]
+    example = Example.from_dict(doc, {"heads": heads, "deps": deps})
+    proj_heads, proj_labels = example.get_aligned_parse(projectivize=True)
+    assert proj_heads == heads
+    assert proj_labels == deps
+
+    # Test documents with no alignments
+    doc_a = Doc(
+        doc.vocab, words=["Double-Jointed"], spaces=[False], deps=["ROOT"], heads=[0]
+    )
+    doc_b = Doc(
+        doc.vocab,
+        words=["Double", "-", "Jointed"],
+        spaces=[True, True, True],
+        deps=["amod", "punct", "ROOT"],
+        heads=[2, 2, 2],
+    )
+    example = Example(doc_a, doc_b)
+    proj_heads, proj_deps = example.get_aligned_parse(projectivize=True)
+    assert proj_heads == [None]
+    assert proj_deps == [None]
+
 
 def test_iob_to_biluo():
     good_iob = ["O", "O", "B-LOC", "I-LOC", "O", "B-PERSON"]

spacy/tests/vocab_vectors/test_similarity.py

@@ -1,6 +1,7 @@
 import pytest
 import numpy
 from spacy.tokens import Doc
+from spacy.vocab import Vocab
 
 from ..util import get_cosine, add_vecs_to_vocab
 
@@ -71,19 +72,17 @@ def test_vectors_similarity_DD(vocab, vectors):
 def test_vectors_similarity_TD(vocab, vectors):
     [(word1, vec1), (word2, vec2)] = vectors
     doc = Doc(vocab, words=[word1, word2])
-    with pytest.warns(UserWarning):
+    assert isinstance(doc.similarity(doc[0]), float)
-        assert isinstance(doc.similarity(doc[0]), float)
+    assert isinstance(doc[0].similarity(doc), float)
-        assert isinstance(doc[0].similarity(doc), float)
+    assert doc.similarity(doc[0]) == doc[0].similarity(doc)
-        assert doc.similarity(doc[0]) == doc[0].similarity(doc)
 
 
 def test_vectors_similarity_TS(vocab, vectors):
     [(word1, vec1), (word2, vec2)] = vectors
     doc = Doc(vocab, words=[word1, word2])
-    with pytest.warns(UserWarning):
+    assert isinstance(doc[:2].similarity(doc[0]), float)
-        assert isinstance(doc[:2].similarity(doc[0]), float)
+    assert isinstance(doc[0].similarity(doc[:2]), float)
-        assert isinstance(doc[0].similarity(doc[-2]), float)
+    assert doc[:2].similarity(doc[0]) == doc[0].similarity(doc[:2])
-        assert doc[:2].similarity(doc[0]) == doc[0].similarity(doc[:2])
 
 
 def test_vectors_similarity_DS(vocab, vectors):
@@ -91,3 +90,21 @@ def test_vectors_similarity_DS(vocab, vectors):
     doc = Doc(vocab, words=[word1, word2])
     assert isinstance(doc.similarity(doc[:2]), float)
     assert doc.similarity(doc[:2]) == doc[:2].similarity(doc)
+
+
+def test_vectors_similarity_no_vectors():
+    vocab = Vocab()
+    doc1 = Doc(vocab, words=["a", "b"])
+    doc2 = Doc(vocab, words=["c", "d", "e"])
+    with pytest.warns(UserWarning):
+        doc1.similarity(doc2)
+    with pytest.warns(UserWarning):
+        doc1.similarity(doc2[1])
+    with pytest.warns(UserWarning):
+        doc1.similarity(doc2[:2])
+    with pytest.warns(UserWarning):
+        doc2.similarity(doc1)
+    with pytest.warns(UserWarning):
+        doc2[1].similarity(doc1)
+    with pytest.warns(UserWarning):
+        doc2[:2].similarity(doc1)

spacy/tests/vocab_vectors/test_vectors.py

@@ -318,17 +318,15 @@ def test_vectors_lexeme_doc_similarity(vocab, text):
 @pytest.mark.parametrize("text", [["apple", "orange", "juice"]])
 def test_vectors_span_span_similarity(vocab, text):
     doc = Doc(vocab, words=text)
-    with pytest.warns(UserWarning):
+    assert doc[0:2].similarity(doc[1:3]) == doc[1:3].similarity(doc[0:2])
-        assert doc[0:2].similarity(doc[1:3]) == doc[1:3].similarity(doc[0:2])
+    assert -1.0 < doc[0:2].similarity(doc[1:3]) < 1.0
-        assert -1.0 < doc[0:2].similarity(doc[1:3]) < 1.0
 
 
 @pytest.mark.parametrize("text", [["apple", "orange", "juice"]])
 def test_vectors_span_doc_similarity(vocab, text):
     doc = Doc(vocab, words=text)
-    with pytest.warns(UserWarning):
+    assert doc[0:2].similarity(doc) == doc.similarity(doc[0:2])
-        assert doc[0:2].similarity(doc) == doc.similarity(doc[0:2])
+    assert -1.0 < doc[0:2].similarity(doc) < 1.0
-        assert -1.0 < doc[0:2].similarity(doc) < 1.0
 
 
 @pytest.mark.parametrize(

spacy/tokens/doc.pyx

@@ -607,7 +607,8 @@ cdef class Doc:
         if self.vocab.vectors.n_keys == 0:
             warnings.warn(Warnings.W007.format(obj="Doc"))
         if self.vector_norm == 0 or other.vector_norm == 0:
-            warnings.warn(Warnings.W008.format(obj="Doc"))
+            if not self.has_vector or not other.has_vector:
+                warnings.warn(Warnings.W008.format(obj="Doc"))
             return 0.0
         vector = self.vector
         xp = get_array_module(vector)
@@ -627,7 +628,7 @@ cdef class Doc:
         if "has_vector" in self.user_hooks:
             return self.user_hooks["has_vector"](self)
         elif self.vocab.vectors.size:
-            return True
+            return any(token.has_vector for token in self)
         elif self.tensor.size:
             return True
         else:

spacy/tokens/span.pyx

@@ -354,7 +354,8 @@ cdef class Span:
         if self.vocab.vectors.n_keys == 0:
             warnings.warn(Warnings.W007.format(obj="Span"))
         if self.vector_norm == 0.0 or other.vector_norm == 0.0:
-            warnings.warn(Warnings.W008.format(obj="Span"))
+            if not self.has_vector or not other.has_vector:
+                warnings.warn(Warnings.W008.format(obj="Span"))
             return 0.0
         vector = self.vector
         xp = get_array_module(vector)

spacy/tokens/token.pyx

@@ -206,7 +206,8 @@ cdef class Token:
         if self.vocab.vectors.n_keys == 0:
             warnings.warn(Warnings.W007.format(obj="Token"))
         if self.vector_norm == 0 or other.vector_norm == 0:
-            warnings.warn(Warnings.W008.format(obj="Token"))
+            if not self.has_vector or not other.has_vector:
+                warnings.warn(Warnings.W008.format(obj="Token"))
             return 0.0
         vector = self.vector
         xp = get_array_module(vector)

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/example.pyx

@@ -13,7 +13,7 @@ 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):
@@ -151,50 +151,127 @@ 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[:]
+        else:
+            gold_i = numpy.vectorize(lambda x: cand_to_gold[int(x)][0], otypes='i')(c2g_single_toks)
+
+        # 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], otypes='i')(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.

spacy/util.py

@@ -1716,3 +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

@@ -336,10 +336,10 @@ cdef class Vectors:
         xp = get_array_module(self.data)
         if key is not None:
             key = get_string_id(key)
-            return self.key2row.get(key, -1)
+            return self.key2row.get(int(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(int(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                                                                                |
@@ -920,5 +920,5 @@ 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.

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/spanruler.md

@@ -2,7 +2,7 @@
 title: SpanRuler
 tag: class
 source: spacy/pipeline/span_ruler.py
-new: 3.3.1
+new: 3.3
 teaser: 'Pipeline component for rule-based span and named entity recognition'
 api_string_name: span_ruler
 api_trainable: false

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/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

@@ -124,6 +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 +1,34 @@
 {
     "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",
@@ -55,7 +84,7 @@
             "code_language": "python",
             "author": "Leap Beyond",
             "author_links": {
-                "github": "https://github.com/LeapBeyond",
+                "github": "LeapBeyond",
                 "website": "https://leapbeyond.ai"
             },
             "code_example": [
@@ -78,8 +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": [
@@ -98,8 +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": [
@@ -571,8 +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": [
@@ -2295,7 +2324,7 @@
             "author": "Daniel Whitenack & Chris Benson",
             "author_links": {
                 "website": "https://changelog.com/practicalai",
-                "twitter": "https://twitter.com/PracticalAIFM"
+                "twitter": "PracticalAIFM"
             },
             "category": ["podcasts"]
         },

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