Merge branch 'master' into feature/config-manipulators

.github/azure-steps.yml

@@ -52,17 +52,17 @@ steps:
       python -W error -c "import spacy"
     displayName: "Test import"
 
-#  - 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: |
+  - script: |
-#      python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
+      python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
-#    displayName: 'Test no warnings on load (#11713)'
+    displayName: 'Test no warnings on load (#11713)'
-#    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 .
@@ -86,17 +86,17 @@ 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 -m pip install -U -r requirements.txt

.github/workflows/autoblack.yml

@@ -16,7 +16,7 @@ jobs:
         with:
             ref: ${{ github.head_ref }}
       - uses: actions/setup-python@v4
-      - run: pip install black
+      - run: pip install black -c requirements.txt
       - name: Auto-format code if needed
         run: black spacy
       # We can't run black --check here because that returns a non-zero excit

.gitignore

@@ -10,16 +10,6 @@ spacy/tests/package/setup.cfg
 spacy/tests/package/pyproject.toml
 spacy/tests/package/requirements.txt
 
-# Website
-website/.cache/
-website/public/
-website/node_modules
-website/.npm
-website/logs
-*.log
-npm-debug.log*
-quickstart-training-generator.js
-
 # Cython / C extensions
 cythonize.json
 spacy/*.html

CONTRIBUTING.md

@@ -173,6 +173,11 @@ formatting and [`flake8`](http://flake8.pycqa.org/en/latest/) for linting its
 Python modules. If you've built spaCy from source, you'll already have both
 tools installed.
 
+As a general rule of thumb, we use f-strings for any formatting of strings.
+One exception are calls to Python's `logging` functionality.
+To avoid unnecessary string conversions in these cases, we use string formatting
+templates with `%s` and `%d` etc.
+
 **⚠️ Note that formatting and linting is currently only possible for Python
 modules in `.py` files, not Cython modules in `.pyx` and `.pxd` files.**
 

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](https://github.com/explosion/spaCy/blob/master/LICENSE).
 
-💫 **Version 3.4 out now!**
+💫 **Version 3.5 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)

azure-pipelines.yml

@@ -11,18 +11,28 @@ trigger:
     exclude:
       - "website/*"
       - "*.md"
+      - "*.mdx"
       - ".github/workflows/*"
 pr:
   paths:
     exclude:
       - "*.md"
+      - "*.mdx"
       - "website/docs/*"
       - "website/src/*"
+      - "website/meta/*.tsx"
+      - "website/meta/*.mjs"
+      - "website/meta/languages.json"
+      - "website/meta/site.json"
+      - "website/meta/sidebars.json"
+      - "website/meta/type-annotations.json"
+      - "website/pages/*"
       - ".github/workflows/*"
 
 jobs:
-  # Perform basic checks for most important errors (syntax etc.) Uses the config
+  # Check formatting and linting. Perform basic checks for most important errors
-  # defined in .flake8 and overwrites the selected codes.
+  # (syntax etc.) Uses the config defined in setup.cfg and overwrites the
+  # selected codes.
   - job: "Validate"
     pool:
       vmImage: "ubuntu-latest"
@@ -30,6 +40,10 @@ jobs:
       - task: UsePythonVersion@0
         inputs:
           versionSpec: "3.7"
+      - script: |
+          pip install black -c requirements.txt
+          python -m black spacy --check
+        displayName: "black"
       - script: |
           pip install flake8==5.0.4
           python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics

requirements.txt

@@ -22,7 +22,7 @@ langcodes>=3.2.0,<4.0.0
 # Official Python utilities
 setuptools
 packaging>=20.0
-typing_extensions>=3.7.4.1,<4.2.0; python_version < "3.8"
+typing_extensions>=3.7.4.1,<4.5.0; python_version < "3.8"
 # Development dependencies
 pre-commit>=2.13.0
 cython>=0.25,<3.0
@@ -31,10 +31,10 @@ pytest-timeout>=1.3.0,<2.0.0
 mock>=2.0.0,<3.0.0
 flake8>=3.8.0,<6.0.0
 hypothesis>=3.27.0,<7.0.0
-mypy>=0.990,<0.1000; platform_machine != "aarch64" and python_version >= "3.7"
+mypy>=0.990,<1.1.0; platform_machine != "aarch64" and python_version >= "3.7"
 types-dataclasses>=0.1.3; python_version < "3.7"
 types-mock>=0.1.1
 types-setuptools>=57.0.0
 types-requests
 types-setuptools>=57.0.0
-black>=22.0,<23.0
+black==22.3.0

setup.cfg

@@ -63,7 +63,7 @@ install_requires =
     # Official Python utilities
     setuptools
     packaging>=20.0
-    typing_extensions>=3.7.4,<4.2.0; python_version < "3.8"
+    typing_extensions>=3.7.4.1,<4.5.0; python_version < "3.8"
     langcodes>=3.2.0,<4.0.0
 
 [options.entry_points]

spacy/cli/__init__.py

@@ -4,6 +4,7 @@ from ._util import app, setup_cli  # noqa: F401
 
 # These are the actual functions, NOT the wrapped CLI commands. The CLI commands
 # are registered automatically and won't have to be imported here.
+from .benchmark_speed import benchmark_speed_cli  # noqa: F401
 from .download import download  # noqa: F401
 from .info import info  # noqa: F401
 from .package import package  # noqa: F401

spacy/cli/_util.py

@@ -46,6 +46,7 @@ DEBUG_HELP = """Suite of helpful commands for debugging and profiling. Includes
 commands to check and validate your config files, training and evaluation data,
 and custom model implementations.
 """
+BENCHMARK_HELP = """Commands for benchmarking pipelines."""
 INIT_HELP = """Commands for initializing configs and pipeline packages."""
 CONFIGURE_HELP = """Commands for automatically modifying configs."""
 
@@ -55,6 +56,7 @@ Arg = typer.Argument
 Opt = typer.Option
 
 app = typer.Typer(name=NAME, help=HELP)
+benchmark_cli = typer.Typer(name="benchmark", help=BENCHMARK_HELP, no_args_is_help=True)
 project_cli = typer.Typer(name="project", help=PROJECT_HELP, no_args_is_help=True)
 debug_cli = typer.Typer(name="debug", help=DEBUG_HELP, no_args_is_help=True)
 init_cli = typer.Typer(name="init", help=INIT_HELP, no_args_is_help=True)
@@ -62,6 +64,7 @@ configure_cli = typer.Typer(name="configure", help=CONFIGURE_HELP, no_args_is_he
 
 app.add_typer(project_cli)
 app.add_typer(debug_cli)
+app.add_typer(benchmark_cli)
 app.add_typer(init_cli)
 app.add_typer(configure_cli)
 
@@ -90,9 +93,9 @@ def parse_config_overrides(
     cli_overrides = _parse_overrides(args, is_cli=True)
     if cli_overrides:
         keys = [k for k in cli_overrides if k not in env_overrides]
-        logger.debug(f"Config overrides from CLI: {keys}")
+        logger.debug("Config overrides from CLI: %s", keys)
     if env_overrides:
-        logger.debug(f"Config overrides from env variables: {list(env_overrides)}")
+        logger.debug("Config overrides from env variables: %s", list(env_overrides))
     return {**cli_overrides, **env_overrides}
 
 

spacy/cli/benchmark_speed.py

@@ -0,0 +1,174 @@
+from typing import Iterable, List, Optional
+import random
+from itertools import islice
+import numpy
+from pathlib import Path
+import time
+from tqdm import tqdm
+import typer
+from wasabi import msg
+
+from .. import util
+from ..language import Language
+from ..tokens import Doc
+from ..training import Corpus
+from ._util import Arg, Opt, benchmark_cli, setup_gpu
+
+
+@benchmark_cli.command(
+    "speed",
+    context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
+)
+def benchmark_speed_cli(
+    # fmt: off
+    ctx: typer.Context,
+    model: str = Arg(..., help="Model name or path"),
+    data_path: Path = Arg(..., help="Location of binary evaluation data in .spacy format", exists=True),
+    batch_size: Optional[int] = Opt(None, "--batch-size", "-b", min=1, help="Override the pipeline batch size"),
+    no_shuffle: bool = Opt(False, "--no-shuffle", help="Do not shuffle benchmark data"),
+    use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
+    n_batches: int = Opt(50, "--batches", help="Minimum number of batches to benchmark", min=30,),
+    warmup_epochs: int = Opt(3, "--warmup", "-w", min=0, help="Number of iterations over the data for warmup"),
+    # fmt: on
+):
+    """
+    Benchmark a pipeline. Expects a loadable spaCy pipeline and benchmark
+    data in the binary .spacy format.
+    """
+    setup_gpu(use_gpu=use_gpu, silent=False)
+
+    nlp = util.load_model(model)
+    batch_size = batch_size if batch_size is not None else nlp.batch_size
+    corpus = Corpus(data_path)
+    docs = [eg.predicted for eg in corpus(nlp)]
+
+    if len(docs) == 0:
+        msg.fail("Cannot benchmark speed using an empty corpus.", exits=1)
+
+    print(f"Warming up for {warmup_epochs} epochs...")
+    warmup(nlp, docs, warmup_epochs, batch_size)
+
+    print()
+    print(f"Benchmarking {n_batches} batches...")
+    wps = benchmark(nlp, docs, n_batches, batch_size, not no_shuffle)
+
+    print()
+    print_outliers(wps)
+    print_mean_with_ci(wps)
+
+
+# Lowercased, behaves as a context manager function.
+class time_context:
+    """Register the running time of a context."""
+
+    def __enter__(self):
+        self.start = time.perf_counter()
+        return self
+
+    def __exit__(self, type, value, traceback):
+        self.elapsed = time.perf_counter() - self.start
+
+
+class Quartiles:
+    """Calculate the q1, q2, q3 quartiles and the inter-quartile range (iqr)
+    of a sample."""
+
+    q1: float
+    q2: float
+    q3: float
+    iqr: float
+
+    def __init__(self, sample: numpy.ndarray) -> None:
+        self.q1 = numpy.quantile(sample, 0.25)
+        self.q2 = numpy.quantile(sample, 0.5)
+        self.q3 = numpy.quantile(sample, 0.75)
+        self.iqr = self.q3 - self.q1
+
+
+def annotate(
+    nlp: Language, docs: List[Doc], batch_size: Optional[int]
+) -> numpy.ndarray:
+    docs = nlp.pipe(tqdm(docs, unit="doc"), batch_size=batch_size)
+    wps = []
+    while True:
+        with time_context() as elapsed:
+            batch_docs = list(
+                islice(docs, batch_size if batch_size else nlp.batch_size)
+            )
+        if len(batch_docs) == 0:
+            break
+        n_tokens = count_tokens(batch_docs)
+        wps.append(n_tokens / elapsed.elapsed)
+
+    return numpy.array(wps)
+
+
+def benchmark(
+    nlp: Language,
+    docs: List[Doc],
+    n_batches: int,
+    batch_size: int,
+    shuffle: bool,
+) -> numpy.ndarray:
+    if shuffle:
+        bench_docs = [
+            nlp.make_doc(random.choice(docs).text)
+            for _ in range(n_batches * batch_size)
+        ]
+    else:
+        bench_docs = [
+            nlp.make_doc(docs[i % len(docs)].text)
+            for i in range(n_batches * batch_size)
+        ]
+
+    return annotate(nlp, bench_docs, batch_size)
+
+
+def bootstrap(x, statistic=numpy.mean, iterations=10000) -> numpy.ndarray:
+    """Apply a statistic to repeated random samples of an array."""
+    return numpy.fromiter(
+        (
+            statistic(numpy.random.choice(x, len(x), replace=True))
+            for _ in range(iterations)
+        ),
+        numpy.float64,
+    )
+
+
+def count_tokens(docs: Iterable[Doc]) -> int:
+    return sum(len(doc) for doc in docs)
+
+
+def print_mean_with_ci(sample: numpy.ndarray):
+    mean = numpy.mean(sample)
+    bootstrap_means = bootstrap(sample)
+    bootstrap_means.sort()
+
+    # 95% confidence interval
+    low = bootstrap_means[int(len(bootstrap_means) * 0.025)]
+    high = bootstrap_means[int(len(bootstrap_means) * 0.975)]
+
+    print(f"Mean: {mean:.1f} words/s (95% CI: {low-mean:.1f} +{high-mean:.1f})")
+
+
+def print_outliers(sample: numpy.ndarray):
+    quartiles = Quartiles(sample)
+
+    n_outliers = numpy.sum(
+        (sample < (quartiles.q1 - 1.5 * quartiles.iqr))
+        | (sample > (quartiles.q3 + 1.5 * quartiles.iqr))
+    )
+    n_extreme_outliers = numpy.sum(
+        (sample < (quartiles.q1 - 3.0 * quartiles.iqr))
+        | (sample > (quartiles.q3 + 3.0 * quartiles.iqr))
+    )
+    print(
+        f"Outliers: {(100 * n_outliers) / len(sample):.1f}%, extreme outliers: {(100 * n_extreme_outliers) / len(sample)}%"
+    )
+
+
+def warmup(
+    nlp: Language, docs: List[Doc], warmup_epochs: int, batch_size: Optional[int]
+) -> numpy.ndarray:
+    docs = warmup_epochs * docs
+    return annotate(nlp, docs, batch_size)

spacy/cli/debug_data.py

@@ -17,6 +17,7 @@ from ..pipeline import TrainablePipe
 from ..pipeline._parser_internals import nonproj
 from ..pipeline._parser_internals.nonproj import DELIMITER
 from ..pipeline import Morphologizer, SpanCategorizer
+from ..pipeline._edit_tree_internals.edit_trees import EditTrees
 from ..morphology import Morphology
 from ..language import Language
 from ..util import registry, resolve_dot_names
@@ -671,6 +672,59 @@ def debug_data(
                 f"Found {gold_train_data['n_cycles']} projectivized train sentence(s) with cycles"
             )
 
+    if "trainable_lemmatizer" in factory_names:
+        msg.divider("Trainable Lemmatizer")
+        trees_train: Set[str] = gold_train_data["lemmatizer_trees"]
+        trees_dev: Set[str] = gold_dev_data["lemmatizer_trees"]
+        # This is necessary context when someone is attempting to interpret whether the
+        # number of trees exclusively in the dev set is meaningful.
+        msg.info(f"{len(trees_train)} lemmatizer trees generated from training data")
+        msg.info(f"{len(trees_dev)} lemmatizer trees generated from dev data")
+        dev_not_train = trees_dev - trees_train
+
+        if len(dev_not_train) != 0:
+            pct = len(dev_not_train) / len(trees_dev)
+            msg.info(
+                f"{len(dev_not_train)} lemmatizer trees ({pct*100:.1f}% of dev trees)"
+                " were found exclusively in the dev data."
+            )
+        else:
+            # Would we ever expect this case? It seems like it would be pretty rare,
+            # and we might actually want a warning?
+            msg.info("All trees in dev data present in training data.")
+
+        if gold_train_data["n_low_cardinality_lemmas"] > 0:
+            n = gold_train_data["n_low_cardinality_lemmas"]
+            msg.warn(f"{n} training docs with 0 or 1 unique lemmas.")
+
+        if gold_dev_data["n_low_cardinality_lemmas"] > 0:
+            n = gold_dev_data["n_low_cardinality_lemmas"]
+            msg.warn(f"{n} dev docs with 0 or 1 unique lemmas.")
+
+        if gold_train_data["no_lemma_annotations"] > 0:
+            n = gold_train_data["no_lemma_annotations"]
+            msg.warn(f"{n} training docs with no lemma annotations.")
+        else:
+            msg.good("All training docs have lemma annotations.")
+
+        if gold_dev_data["no_lemma_annotations"] > 0:
+            n = gold_dev_data["no_lemma_annotations"]
+            msg.warn(f"{n} dev docs with no lemma annotations.")
+        else:
+            msg.good("All dev docs have lemma annotations.")
+
+        if gold_train_data["partial_lemma_annotations"] > 0:
+            n = gold_train_data["partial_lemma_annotations"]
+            msg.info(f"{n} training docs with partial lemma annotations.")
+        else:
+            msg.good("All training docs have complete lemma annotations.")
+
+        if gold_dev_data["partial_lemma_annotations"] > 0:
+            n = gold_dev_data["partial_lemma_annotations"]
+            msg.info(f"{n} dev docs with partial lemma annotations.")
+        else:
+            msg.good("All dev docs have complete lemma annotations.")
+
     msg.divider("Summary")
     good_counts = msg.counts[MESSAGES.GOOD]
     warn_counts = msg.counts[MESSAGES.WARN]
@@ -732,7 +786,13 @@ def _compile_gold(
         "n_cats_multilabel": 0,
         "n_cats_bad_values": 0,
         "texts": set(),
+        "lemmatizer_trees": set(),
+        "no_lemma_annotations": 0,
+        "partial_lemma_annotations": 0,
+        "n_low_cardinality_lemmas": 0,
     }
+    if "trainable_lemmatizer" in factory_names:
+        trees = EditTrees(nlp.vocab.strings)
     for eg in examples:
         gold = eg.reference
         doc = eg.predicted
@@ -862,6 +922,25 @@ def _compile_gold(
                 data["n_nonproj"] += 1
             if nonproj.contains_cycle(aligned_heads):
                 data["n_cycles"] += 1
+        if "trainable_lemmatizer" in factory_names:
+            # from EditTreeLemmatizer._labels_from_data
+            if all(token.lemma == 0 for token in gold):
+                data["no_lemma_annotations"] += 1
+                continue
+            if any(token.lemma == 0 for token in gold):
+                data["partial_lemma_annotations"] += 1
+            lemma_set = set()
+            for token in gold:
+                if token.lemma != 0:
+                    lemma_set.add(token.lemma)
+                    tree_id = trees.add(token.text, token.lemma_)
+                    tree_str = trees.tree_to_str(tree_id)
+                    data["lemmatizer_trees"].add(tree_str)
+            # We want to identify cases where lemmas aren't assigned
+            # or are all assigned the same value, as this would indicate
+            # an issue since we're expecting a large set of lemmas
+            if len(lemma_set) < 2 and len(gold) > 1:
+                data["n_low_cardinality_lemmas"] += 1
     return data
 
 

spacy/cli/evaluate.py

@@ -7,12 +7,15 @@ from thinc.api import fix_random_seed
 
 from ..training import Corpus
 from ..tokens import Doc
-from ._util import app, Arg, Opt, setup_gpu, import_code
+from ._util import app, Arg, Opt, setup_gpu, import_code, benchmark_cli
 from ..scorer import Scorer
 from .. import util
 from .. import displacy
 
 
+@benchmark_cli.command(
+    "accuracy",
+)
 @app.command("evaluate")
 def evaluate_cli(
     # fmt: off
@@ -36,7 +39,7 @@ def evaluate_cli(
     dependency parses in a HTML file, set as output directory as the
     displacy_path argument.
 
-    DOCS: https://spacy.io/api/cli#evaluate
+    DOCS: https://spacy.io/api/cli#benchmark-accuracy
     """
     import_code(code_path)
     evaluate(

spacy/cli/project/pull.py

@@ -39,14 +39,17 @@ def project_pull(project_dir: Path, remote: str, *, verbose: bool = False):
     # in the list.
     while commands:
         for i, cmd in enumerate(list(commands)):
-            logger.debug(f"CMD: {cmd['name']}.")
+            logger.debug("CMD: %s.", cmd["name"])
             deps = [project_dir / dep for dep in cmd.get("deps", [])]
             if all(dep.exists() for dep in deps):
                 cmd_hash = get_command_hash("", "", deps, cmd["script"])
                 for output_path in cmd.get("outputs", []):
                     url = storage.pull(output_path, command_hash=cmd_hash)
                     logger.debug(
-                        f"URL: {url} for {output_path} with command hash {cmd_hash}"
+                        "URL: %s for %s with command hash %s",
+                        url,
+                        output_path,
+                        cmd_hash,
                     )
                     yield url, output_path
 
@@ -58,7 +61,7 @@ def project_pull(project_dir: Path, remote: str, *, verbose: bool = False):
                 commands.pop(i)
                 break
             else:
-                logger.debug(f"Dependency missing. Skipping {cmd['name']} outputs.")
+                logger.debug("Dependency missing. Skipping %s outputs.", cmd["name"])
         else:
             # If we didn't break the for loop, break the while loop.
             break

spacy/cli/project/push.py

@@ -37,15 +37,15 @@ def project_push(project_dir: Path, remote: str):
         remote = config["remotes"][remote]
     storage = RemoteStorage(project_dir, remote)
     for cmd in config.get("commands", []):
-        logger.debug(f"CMD: cmd['name']")
+        logger.debug("CMD: %s", cmd["name"])
         deps = [project_dir / dep for dep in cmd.get("deps", [])]
         if any(not dep.exists() for dep in deps):
-            logger.debug(f"Dependency missing. Skipping {cmd['name']} outputs")
+            logger.debug("Dependency missing. Skipping %s outputs", cmd["name"])
             continue
         cmd_hash = get_command_hash(
             "", "", [project_dir / dep for dep in cmd.get("deps", [])], cmd["script"]
         )
-        logger.debug(f"CMD_HASH: {cmd_hash}")
+        logger.debug("CMD_HASH: %s", cmd_hash)
         for output_path in cmd.get("outputs", []):
             output_loc = project_dir / output_path
             if output_loc.exists() and _is_not_empty_dir(output_loc):
@@ -55,7 +55,7 @@ def project_push(project_dir: Path, remote: str):
                     content_hash=get_content_hash(output_loc),
                 )
                 logger.debug(
-                    f"URL: {url} for output {output_path} with cmd_hash {cmd_hash}"
+                    "URL: %s for output %s with cmd_hash %s", url, output_path, cmd_hash
                 )
                 yield output_path, url
 

spacy/displacy/__init__.py

@@ -106,9 +106,7 @@ def serve(
 
     if is_in_jupyter():
         warnings.warn(Warnings.W011)
-    render(
+    render(docs, style=style, page=page, minify=minify, options=options, manual=manual)
-        docs, style=style, page=page, minify=minify, options=options, manual=manual
-    )
     httpd = simple_server.make_server(host, port, app)
     print(f"\nUsing the '{style}' visualizer")
     print(f"Serving on http://{host}:{port} ...\n")

spacy/errors.py

@@ -965,8 +965,8 @@ class Errors(metaclass=ErrorsWithCodes):
     E1047 = ("`find_threshold()` only supports components with a `scorer` attribute.")
     E1048 = ("Got '{unexpected}' as console progress bar type, but expected one of the following: {expected}")
     E1049 = ("No available port found for displaCy on host {host}. Please specify an available port "
-             "with `displacy.serve(doc, port)`")
+             "with `displacy.serve(doc, port=port)`")
-    E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port)` "
+    E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port=port)` "
              "or use `auto_switch_port=True` to pick an available port automatically.")
 
 

spacy/kb/kb_in_memory.pyx

@@ -25,7 +25,7 @@ cdef class InMemoryLookupKB(KnowledgeBase):
     """An `InMemoryLookupKB` instance stores unique identifiers for entities and their textual aliases,
     to support entity linking of named entities to real-world concepts.
 
-    DOCS: https://spacy.io/api/kb_in_memory
+    DOCS: https://spacy.io/api/inmemorylookupkb
     """
 
     def __init__(self, Vocab vocab, entity_vector_length):

spacy/language.py

@@ -104,7 +104,7 @@ def create_tokenizer() -> Callable[["Language"], Tokenizer]:
 
 @registry.misc("spacy.LookupsDataLoader.v1")
 def load_lookups_data(lang, tables):
-    util.logger.debug(f"Loading lookups from spacy-lookups-data: {tables}")
+    util.logger.debug("Loading lookups from spacy-lookups-data: %s", tables)
     lookups = load_lookups(lang=lang, tables=tables)
     return lookups
 
@@ -1969,7 +1969,7 @@ class Language:
         pipe = self.get_pipe(pipe_name)
         pipe_cfg = self._pipe_configs[pipe_name]
         if listeners:
-            util.logger.debug(f"Replacing listeners of component '{pipe_name}'")
+            util.logger.debug("Replacing listeners of component '%s'", pipe_name)
             if len(list(listeners)) != len(pipe_listeners):
                 # The number of listeners defined in the component model doesn't
                 # match the listeners to replace, so we won't be able to update

spacy/matcher/levenshtein.pyx

@@ -22,7 +22,7 @@ cpdef bint levenshtein_compare(input_text: str, pattern_text: str, fuzzy: int =
         max_edits = fuzzy
     else:
         # allow at least two edits (to allow at least one transposition) and up
-        # to 20% of the pattern string length
+        # to 30% of the pattern string length
         max_edits = max(2, round(0.3 * len(pattern_text)))
     return levenshtein(input_text, pattern_text, max_edits) <= max_edits
 

spacy/matcher/matcher.pyi

@@ -5,8 +5,12 @@ from ..vocab import Vocab
 from ..tokens import Doc, Span
 
 class Matcher:
-    def __init__(self, vocab: Vocab, validate: bool = ...,
+    def __init__(
-                 fuzzy_compare: Callable[[str, str, int], bool] = ...) -> None: ...
+        self,
+        vocab: Vocab,
+        validate: bool = ...,
+        fuzzy_compare: Callable[[str, str, int], bool] = ...,
+    ) -> None: ...
     def __reduce__(self) -> Any: ...
     def __len__(self) -> int: ...
     def __contains__(self, key: str) -> bool: ...

spacy/pipeline/edit_tree_lemmatizer.py

@@ -5,8 +5,8 @@ from itertools import islice
 import numpy as np
 
 import srsly
-from thinc.api import Config, Model, SequenceCategoricalCrossentropy
+from thinc.api import Config, Model, SequenceCategoricalCrossentropy, NumpyOps
-from thinc.types import Floats2d, Ints1d, Ints2d
+from thinc.types import Floats2d, Ints2d
 
 from ._edit_tree_internals.edit_trees import EditTrees
 from ._edit_tree_internals.schemas import validate_edit_tree
@@ -20,6 +20,10 @@ from ..vocab import Vocab
 from .. import util
 
 
+# The cutoff value of *top_k* above which an alternative method is used to process guesses.
+TOP_K_GUARDRAIL = 20
+
+
 default_model_config = """
 [model]
 @architectures = "spacy.Tagger.v2"
@@ -115,6 +119,7 @@ class EditTreeLemmatizer(TrainablePipe):
 
         self.cfg: Dict[str, Any] = {"labels": []}
         self.scorer = scorer
+        self.numpy_ops = NumpyOps()
 
     def get_loss(
         self, examples: Iterable[Example], scores: List[Floats2d]
@@ -128,7 +133,7 @@ class EditTreeLemmatizer(TrainablePipe):
             for (predicted, gold_lemma) in zip(
                 eg.predicted, eg.get_aligned("LEMMA", as_string=True)
             ):
-                if gold_lemma is None:
+                if gold_lemma is None or gold_lemma == "":
                     label = -1
                 else:
                     tree_id = self.trees.add(predicted.text, gold_lemma)
@@ -144,6 +149,18 @@ class EditTreeLemmatizer(TrainablePipe):
         return float(loss), d_scores
 
     def predict(self, docs: Iterable[Doc]) -> List[Ints2d]:
+        if self.top_k == 1:
+            scores2guesses = self._scores2guesses_top_k_equals_1
+        elif self.top_k <= TOP_K_GUARDRAIL:
+            scores2guesses = self._scores2guesses_top_k_greater_1
+        else:
+            scores2guesses = self._scores2guesses_top_k_guardrail
+        # The behaviour of *_scores2guesses_top_k_greater_1()* is efficient for values
+        # of *top_k>1* that are likely to be useful when the edit tree lemmatizer is used
+        # for its principal purpose of lemmatizing tokens. However, the code could also
+        # be used for other purposes, and with very large values of *top_k* the method
+        # becomes inefficient. In such cases, *_scores2guesses_top_k_guardrail()* is used
+        # instead.
         n_docs = len(list(docs))
         if not any(len(doc) for doc in docs):
             # Handle cases where there are no tokens in any docs.
@@ -153,20 +170,52 @@ class EditTreeLemmatizer(TrainablePipe):
             return guesses
         scores = self.model.predict(docs)
         assert len(scores) == n_docs
-        guesses = self._scores2guesses(docs, scores)
+        guesses = scores2guesses(docs, scores)
         assert len(guesses) == n_docs
         return guesses
 
-    def _scores2guesses(self, docs, scores):
+    def _scores2guesses_top_k_equals_1(self, docs, scores):
         guesses = []
         for doc, doc_scores in zip(docs, scores):
-            if self.top_k == 1:
+            doc_guesses = doc_scores.argmax(axis=1)
-                doc_guesses = doc_scores.argmax(axis=1).reshape(-1, 1)
+            doc_guesses = self.numpy_ops.asarray(doc_guesses)
-            else:
-                doc_guesses = np.argsort(doc_scores)[..., : -self.top_k - 1 : -1]
 
-            if not isinstance(doc_guesses, np.ndarray):
+            doc_compat_guesses = []
-                doc_guesses = doc_guesses.get()
+            for i, token in enumerate(doc):
+                tree_id = self.cfg["labels"][doc_guesses[i]]
+                if self.trees.apply(tree_id, token.text) is not None:
+                    doc_compat_guesses.append(tree_id)
+                else:
+                    doc_compat_guesses.append(-1)
+            guesses.append(np.array(doc_compat_guesses))
+
+        return guesses
+
+    def _scores2guesses_top_k_greater_1(self, docs, scores):
+        guesses = []
+        top_k = min(self.top_k, len(self.labels))
+        for doc, doc_scores in zip(docs, scores):
+            doc_scores = self.numpy_ops.asarray(doc_scores)
+            doc_compat_guesses = []
+            for i, token in enumerate(doc):
+                for _ in range(top_k):
+                    candidate = int(doc_scores[i].argmax())
+                    candidate_tree_id = self.cfg["labels"][candidate]
+                    if self.trees.apply(candidate_tree_id, token.text) is not None:
+                        doc_compat_guesses.append(candidate_tree_id)
+                        break
+                    doc_scores[i, candidate] = np.finfo(np.float32).min
+                else:
+                    doc_compat_guesses.append(-1)
+            guesses.append(np.array(doc_compat_guesses))
+
+        return guesses
+
+    def _scores2guesses_top_k_guardrail(self, docs, scores):
+        guesses = []
+        for doc, doc_scores in zip(docs, scores):
+            doc_guesses = np.argsort(doc_scores)[..., : -self.top_k - 1 : -1]
+            doc_guesses = self.numpy_ops.asarray(doc_guesses)
 
             doc_compat_guesses = []
             for token, candidates in zip(doc, doc_guesses):

spacy/schemas.py

@@ -163,15 +163,33 @@ class TokenPatternString(BaseModel):
     IS_SUPERSET: Optional[List[StrictStr]] = Field(None, alias="is_superset")
     INTERSECTS: Optional[List[StrictStr]] = Field(None, alias="intersects")
     FUZZY: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy")
-    FUZZY1: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy1")
+    FUZZY1: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
-    FUZZY2: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy2")
+        None, alias="fuzzy1"
-    FUZZY3: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy3")
+    )
-    FUZZY4: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy4")
+    FUZZY2: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
-    FUZZY5: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy5")
+        None, alias="fuzzy2"
-    FUZZY6: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy6")
+    )
-    FUZZY7: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy7")
+    FUZZY3: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
-    FUZZY8: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy8")
+        None, alias="fuzzy3"
-    FUZZY9: Optional[Union[StrictStr, "TokenPatternString"]] = Field(None, alias="fuzzy9")
+    )
+    FUZZY4: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy4"
+    )
+    FUZZY5: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy5"
+    )
+    FUZZY6: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy6"
+    )
+    FUZZY7: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy7"
+    )
+    FUZZY8: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy8"
+    )
+    FUZZY9: Optional[Union[StrictStr, "TokenPatternString"]] = Field(
+        None, alias="fuzzy9"
+    )
 
     class Config:
         extra = "forbid"

spacy/tests/doc/test_span.py

@@ -163,6 +163,18 @@ def test_char_span(doc, i_sent, i, j, text):
         assert span.text == text
 
 
+def test_char_span_attributes(doc):
+    label = "LABEL"
+    kb_id = "KB_ID"
+    span_id = "SPAN_ID"
+    span1 = doc.char_span(20, 45, label=label, kb_id=kb_id, span_id=span_id)
+    span2 = doc[1:].char_span(15, 40, label=label, kb_id=kb_id, span_id=span_id)
+    assert span1.text == span2.text
+    assert span1.label_ == span2.label_ == label
+    assert span1.kb_id_ == span2.kb_id_ == kb_id
+    assert span1.id_ == span2.id_ == span_id
+
+
 def test_spans_sent_spans(doc):
     sents = list(doc.sents)
     assert sents[0].start == 0
@@ -367,6 +379,14 @@ def test_spans_by_character(doc):
             span1.start_char + 1, span1.end_char, label="GPE", alignment_mode="unk"
         )
 
+    # Span.char_span + alignment mode "contract"
+    span2 = doc[0:2].char_span(
+        span1.start_char - 3, span1.end_char, label="GPE", alignment_mode="contract"
+    )
+    assert span1.start_char == span2.start_char
+    assert span1.end_char == span2.end_char
+    assert span2.label_ == "GPE"
+
 
 def test_span_to_array(doc):
     span = doc[1:-2]

spacy/tests/pipeline/test_edit_tree_lemmatizer.py

@@ -101,14 +101,15 @@ def test_initialize_from_labels():
     }
 
 
-def test_no_data():
+@pytest.mark.parametrize("top_k", (1, 5, 30))
+def test_no_data(top_k):
     # Test that the lemmatizer provides a nice error when there's no tagging data / labels
     TEXTCAT_DATA = [
         ("I'm so happy.", {"cats": {"POSITIVE": 1.0, "NEGATIVE": 0.0}}),
         ("I'm so angry", {"cats": {"POSITIVE": 0.0, "NEGATIVE": 1.0}}),
     ]
     nlp = English()
-    nlp.add_pipe("trainable_lemmatizer")
+    nlp.add_pipe("trainable_lemmatizer", config={"top_k": top_k})
     nlp.add_pipe("textcat")
 
     train_examples = []
@@ -119,10 +120,11 @@ def test_no_data():
         nlp.initialize(get_examples=lambda: train_examples)
 
 
-def test_incomplete_data():
+@pytest.mark.parametrize("top_k", (1, 5, 30))
+def test_incomplete_data(top_k):
     # Test that the lemmatizer works with incomplete information
     nlp = English()
-    lemmatizer = nlp.add_pipe("trainable_lemmatizer")
+    lemmatizer = nlp.add_pipe("trainable_lemmatizer", config={"top_k": top_k})
     lemmatizer.min_tree_freq = 1
     train_examples = []
     for t in PARTIAL_DATA:
@@ -139,10 +141,25 @@ def test_incomplete_data():
     assert doc[1].lemma_ == "like"
     assert doc[2].lemma_ == "blue"
 
+    # Check that incomplete annotations are ignored.
+    scores, _ = lemmatizer.model([eg.predicted for eg in train_examples], is_train=True)
+    _, dX = lemmatizer.get_loss(train_examples, scores)
+    xp = lemmatizer.model.ops.xp
 
-def test_overfitting_IO():
+    # Missing annotations.
+    assert xp.count_nonzero(dX[0][0]) == 0
+    assert xp.count_nonzero(dX[0][3]) == 0
+    assert xp.count_nonzero(dX[1][0]) == 0
+    assert xp.count_nonzero(dX[1][3]) == 0
+
+    # Misaligned annotations.
+    assert xp.count_nonzero(dX[1][1]) == 0
+
+
+@pytest.mark.parametrize("top_k", (1, 5, 30))
+def test_overfitting_IO(top_k):
     nlp = English()
-    lemmatizer = nlp.add_pipe("trainable_lemmatizer")
+    lemmatizer = nlp.add_pipe("trainable_lemmatizer", config={"top_k": top_k})
     lemmatizer.min_tree_freq = 1
     train_examples = []
     for t in TRAIN_DATA:
@@ -175,7 +192,7 @@ def test_overfitting_IO():
     # Check model after a {to,from}_bytes roundtrip
     nlp_bytes = nlp.to_bytes()
     nlp3 = English()
-    nlp3.add_pipe("trainable_lemmatizer")
+    nlp3.add_pipe("trainable_lemmatizer", config={"top_k": top_k})
     nlp3.from_bytes(nlp_bytes)
     doc3 = nlp3(test_text)
     assert doc3[0].lemma_ == "she"

spacy/tests/test_cli.py

@@ -620,7 +620,6 @@ 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
@@ -631,7 +630,6 @@ 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
@@ -1021,8 +1019,6 @@ def test_local_remote_storage_pull_missing():
 
 
 def test_cli_find_threshold(capsys):
-    thresholds = numpy.linspace(0, 1, 10)
-
     def make_examples(nlp: Language) -> List[Example]:
         docs: List[Example] = []
 
@@ -1078,7 +1074,7 @@ def test_cli_find_threshold(capsys):
         )
         with make_tempdir() as nlp_dir:
             nlp.to_disk(nlp_dir)
-            res = find_threshold(
+            best_threshold, best_score, res = find_threshold(
                 model=nlp_dir,
                 data_path=docs_dir / "docs.spacy",
                 pipe_name="tc_multi",
@@ -1086,16 +1082,14 @@ def test_cli_find_threshold(capsys):
                 scores_key="cats_macro_f",
                 silent=True,
             )
-            assert res[0] != thresholds[0]
+            assert best_score == max(res.values())
-            assert thresholds[0] < res[0] < thresholds[9]
+            assert res[1.0] == 0.0
-            assert res[1] == 1.0
-            assert res[2][1.0] == 0.0
 
         # Test with spancat.
         nlp, _ = init_nlp((("spancat", {}),))
         with make_tempdir() as nlp_dir:
             nlp.to_disk(nlp_dir)
-            res = find_threshold(
+            best_threshold, best_score, res = find_threshold(
                 model=nlp_dir,
                 data_path=docs_dir / "docs.spacy",
                 pipe_name="spancat",
@@ -1103,10 +1097,8 @@ def test_cli_find_threshold(capsys):
                 scores_key="spans_sc_f",
                 silent=True,
             )
-            assert res[0] != thresholds[0]
+            assert best_score == max(res.values())
-            assert thresholds[0] < res[0] < thresholds[8]
+            assert res[1.0] == 0.0
-            assert res[1] >= 0.6
-            assert res[2][1.0] == 0.0
 
         # Having multiple textcat_multilabel components should work, since the name has to be specified.
         nlp, _ = init_nlp((("textcat_multilabel", {}),))
@@ -1276,3 +1268,69 @@ def test_walk_directory():
         assert (len(walk_directory(d, suffix="iob"))) == 2
         assert (len(walk_directory(d, suffix="conll"))) == 3
         assert (len(walk_directory(d, suffix="pdf"))) == 0
+
+
+def test_debug_data_trainable_lemmatizer_basic():
+    examples = [
+        ("She likes green eggs", {"lemmas": ["she", "like", "green", "egg"]}),
+        ("Eat blue ham", {"lemmas": ["eat", "blue", "ham"]}),
+    ]
+    nlp = Language()
+    train_examples = []
+    for t in examples:
+        train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
+
+    data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
+    # ref test_edit_tree_lemmatizer::test_initialize_from_labels
+    # this results in 4 trees
+    assert len(data["lemmatizer_trees"]) == 4
+
+
+def test_debug_data_trainable_lemmatizer_partial():
+    partial_examples = [
+        # partial annotation
+        ("She likes green eggs", {"lemmas": ["", "like", "green", ""]}),
+        # misaligned partial annotation
+        (
+            "He hates green eggs",
+            {
+                "words": ["He", "hat", "es", "green", "eggs"],
+                "lemmas": ["", "hat", "e", "green", ""],
+            },
+        ),
+    ]
+    nlp = Language()
+    train_examples = []
+    for t in partial_examples:
+        train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
+
+    data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
+    assert data["partial_lemma_annotations"] == 2
+
+
+def test_debug_data_trainable_lemmatizer_low_cardinality():
+    low_cardinality_examples = [
+        ("She likes green eggs", {"lemmas": ["no", "no", "no", "no"]}),
+        ("Eat blue ham", {"lemmas": ["no", "no", "no"]}),
+    ]
+    nlp = Language()
+    train_examples = []
+    for t in low_cardinality_examples:
+        train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
+
+    data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
+    assert data["n_low_cardinality_lemmas"] == 2
+
+
+def test_debug_data_trainable_lemmatizer_not_annotated():
+    unannotated_examples = [
+        ("She likes green eggs", {}),
+        ("Eat blue ham", {}),
+    ]
+    nlp = Language()
+    train_examples = []
+    for t in unannotated_examples:
+        train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
+
+    data = _compile_gold(train_examples, ["trainable_lemmatizer"], nlp, True)
+    assert data["no_lemma_annotations"] == 2

spacy/tests/test_cli_app.py

@@ -1,9 +1,10 @@
 import os
 from pathlib import Path
 from typer.testing import CliRunner
+from spacy.tokens import DocBin, Doc
 
 from spacy.cli._util import app
-from .util import make_tempdir
+from .util import make_tempdir, normalize_whitespace
 
 
 def test_convert_auto():
@@ -31,3 +32,60 @@ def test_convert_auto_conflict():
         assert "All input files must be same type" in result.stdout
         out_files = os.listdir(d_out)
         assert len(out_files) == 0
+
+
+def test_benchmark_accuracy_alias():
+    # Verify that the `evaluate` alias works correctly.
+    result_benchmark = CliRunner().invoke(app, ["benchmark", "accuracy", "--help"])
+    result_evaluate = CliRunner().invoke(app, ["evaluate", "--help"])
+    assert normalize_whitespace(result_benchmark.stdout) == normalize_whitespace(
+        result_evaluate.stdout.replace("spacy evaluate", "spacy benchmark accuracy")
+    )
+
+
+def test_debug_data_trainable_lemmatizer_cli(en_vocab):
+    train_docs = [
+        Doc(en_vocab, words=["I", "like", "cats"], lemmas=["I", "like", "cat"]),
+        Doc(
+            en_vocab,
+            words=["Dogs", "are", "great", "too"],
+            lemmas=["dog", "be", "great", "too"],
+        ),
+    ]
+    dev_docs = [
+        Doc(en_vocab, words=["Cats", "are", "cute"], lemmas=["cat", "be", "cute"]),
+        Doc(en_vocab, words=["Pets", "are", "great"], lemmas=["pet", "be", "great"]),
+    ]
+    with make_tempdir() as d_in:
+        train_bin = DocBin(docs=train_docs)
+        train_bin.to_disk(d_in / "train.spacy")
+        dev_bin = DocBin(docs=dev_docs)
+        dev_bin.to_disk(d_in / "dev.spacy")
+        # `debug data` requires an input pipeline config
+        CliRunner().invoke(
+            app,
+            [
+                "init",
+                "config",
+                f"{d_in}/config.cfg",
+                "--lang",
+                "en",
+                "--pipeline",
+                "trainable_lemmatizer",
+            ],
+        )
+        result_debug_data = CliRunner().invoke(
+            app,
+            [
+                "debug",
+                "data",
+                f"{d_in}/config.cfg",
+                "--paths.train",
+                f"{d_in}/train.spacy",
+                "--paths.dev",
+                f"{d_in}/dev.spacy",
+            ],
+        )
+        # Instead of checking specific wording of the output, which may change,
+        # we'll check that this section of the debug output is present.
+        assert "= Trainable Lemmatizer =" in result_debug_data.stdout

spacy/tests/test_language.py

@@ -46,7 +46,7 @@ def assert_sents_error(doc):
 
 def warn_error(proc_name, proc, docs, e):
     logger = logging.getLogger("spacy")
-    logger.warning(f"Trouble with component {proc_name}.")
+    logger.warning("Trouble with component %s.", proc_name)
 
 
 @pytest.fixture

spacy/tests/training/test_corpus.py

@@ -0,0 +1,78 @@
+from typing import IO, Generator, Iterable, List, TextIO, Tuple
+from contextlib import contextmanager
+from pathlib import Path
+import pytest
+import tempfile
+
+from spacy.lang.en import English
+from spacy.training import Example, PlainTextCorpus
+from spacy.util import make_tempdir
+
+# Intentional newlines to check that they are skipped.
+PLAIN_TEXT_DOC = """
+
+This is a doc. It contains two sentences.
+This is another doc.
+
+A third doc.
+
+"""
+
+PLAIN_TEXT_DOC_TOKENIZED = [
+    [
+        "This",
+        "is",
+        "a",
+        "doc",
+        ".",
+        "It",
+        "contains",
+        "two",
+        "sentences",
+        ".",
+    ],
+    ["This", "is", "another", "doc", "."],
+    ["A", "third", "doc", "."],
+]
+
+
+@pytest.mark.parametrize("min_length", [0, 5])
+@pytest.mark.parametrize("max_length", [0, 5])
+def test_plain_text_reader(min_length, max_length):
+    nlp = English()
+    with _string_to_tmp_file(PLAIN_TEXT_DOC) as file_path:
+        corpus = PlainTextCorpus(
+            file_path, min_length=min_length, max_length=max_length
+        )
+
+        check = [
+            doc
+            for doc in PLAIN_TEXT_DOC_TOKENIZED
+            if len(doc) >= min_length and (max_length == 0 or len(doc) <= max_length)
+        ]
+        reference, predicted = _examples_to_tokens(corpus(nlp))
+
+        assert reference == check
+        assert predicted == check
+
+
+@contextmanager
+def _string_to_tmp_file(s: str) -> Generator[Path, None, None]:
+    with make_tempdir() as d:
+        file_path = Path(d) / "string.txt"
+        with open(file_path, "w", encoding="utf-8") as f:
+            f.write(s)
+        yield file_path
+
+
+def _examples_to_tokens(
+    examples: Iterable[Example],
+) -> Tuple[List[List[str]], List[List[str]]]:
+    reference = []
+    predicted = []
+
+    for eg in examples:
+        reference.append([t.text for t in eg.reference])
+        predicted.append([t.text for t in eg.predicted])
+
+    return reference, predicted

spacy/tests/util.py

@@ -1,6 +1,7 @@
 import numpy
 import tempfile
 import contextlib
+import re
 import srsly
 from spacy.tokens import Doc
 from spacy.vocab import Vocab
@@ -95,3 +96,7 @@ def assert_packed_msg_equal(b1, b2):
     for (k1, v1), (k2, v2) in zip(sorted(msg1.items()), sorted(msg2.items())):
         assert k1 == k2
         assert v1 == v2
+
+
+def normalize_whitespace(s):
+    return re.sub(r"\s+", " ", s)

spacy/tokens/doc.pyi

@@ -108,6 +108,7 @@ class Doc:
         kb_id: Union[int, str] = ...,
         vector: Optional[Floats1d] = ...,
         alignment_mode: str = ...,
+        span_id: Union[int, str] = ...,
     ) -> Span: ...
     def similarity(self, other: Union[Doc, Span, Token, Lexeme]) -> float: ...
     @property

spacy/tokens/doc.pyx

@@ -528,9 +528,9 @@ cdef class Doc:
         doc (Doc): The parent document.
         start_idx (int): The index of the first character of the span.
         end_idx (int): The index of the first character after the span.
-        label (uint64 or string): A label to attach to the Span, e.g. for
+        label (Union[int, str]): A label to attach to the Span, e.g. for
             named entities.
-        kb_id (uint64 or string):  An ID from a KB to capture the meaning of a
+        kb_id (Union[int, str]):  An ID from a KB to capture the meaning of a
             named entity.
         vector (ndarray[ndim=1, dtype='float32']): A meaning representation of
             the span.
@@ -539,6 +539,7 @@ cdef class Doc:
             with token boundaries), "contract" (span of all tokens completely
             within the character span), "expand" (span of all tokens at least
             partially covered by the character span). Defaults to "strict".
+        span_id (Union[int, str]): An identifier to associate with the span.
         RETURNS (Span): The newly constructed object.
 
         DOCS: https://spacy.io/api/doc#char_span

spacy/tokens/span.pyi

@@ -98,6 +98,9 @@ class Span:
         label: Union[int, str] = ...,
         kb_id: Union[int, str] = ...,
         vector: Optional[Floats1d] = ...,
+        id: Union[int, str] = ...,
+        alignment_mode: str = ...,
+        span_id: Union[int, str] = ...,
     ) -> Span: ...
     @property
     def conjuncts(self) -> Tuple[Token]: ...

spacy/tokens/span.pyx

@@ -362,7 +362,7 @@ cdef class Span:
         result = xp.dot(vector, other.vector) / (self.vector_norm * other.vector_norm)
         # ensure we get a scalar back (numpy does this automatically but cupy doesn't)
         return result.item()
-    
+
     cpdef np.ndarray to_array(self, object py_attr_ids):
         """Given a list of M attribute IDs, export the tokens to a numpy
         `ndarray` of shape `(N, M)`, where `N` is the length of the document.
@@ -639,21 +639,28 @@ 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, id=0):
+    def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, id=0, alignment_mode="strict", span_id=0):
         """Create a `Span` object from the slice `span.text[start : end]`.
 
         start (int): The index of the first character of the span.
         end (int): The index of the first character after the span.
-        label (uint64 or string): A label to attach to the Span, e.g. for
+        label (Union[int, str]): A label to attach to the Span, e.g. for
             named entities.
-        kb_id (uint64 or string):  An ID from a KB to capture the meaning of a named entity.
+        kb_id (Union[int, str]):  An ID from a KB to capture the meaning of a named entity.
         vector (ndarray[ndim=1, dtype='float32']): A meaning representation of
             the span.
+        id (Union[int, str]): Unused.
+        alignment_mode (str): How character indices are aligned to token
+            boundaries. Options: "strict" (character indices must be aligned
+            with token boundaries), "contract" (span of all tokens completely
+            within the character span), "expand" (span of all tokens at least
+            partially covered by the character span). Defaults to "strict".
+        span_id (Union[int, str]): An identifier to associate with the span.
         RETURNS (Span): The newly constructed object.
         """
         start_idx += self.c.start_char
         end_idx += self.c.start_char
-        return self.doc.char_span(start_idx, end_idx, label=label, kb_id=kb_id, vector=vector)
+        return self.doc.char_span(start_idx, end_idx, label=label, kb_id=kb_id, vector=vector, alignment_mode=alignment_mode, span_id=span_id)
 
     @property
     def conjuncts(self):

spacy/training/__init__.py

@@ -1,4 +1,4 @@
-from .corpus import Corpus, JsonlCorpus  # noqa: F401
+from .corpus import Corpus, JsonlCorpus, PlainTextCorpus  # noqa: F401
 from .example import Example, validate_examples, validate_get_examples  # noqa: F401
 from .alignment import Alignment  # noqa: F401
 from .augment import dont_augment, orth_variants_augmenter  # noqa: F401

spacy/training/callbacks.py

@@ -11,7 +11,7 @@ def create_copy_from_base_model(
 ) -> Callable[[Language], Language]:
     def copy_from_base_model(nlp):
         if tokenizer:
-            logger.info(f"Copying tokenizer from: {tokenizer}")
+            logger.info("Copying tokenizer from: %s", tokenizer)
             base_nlp = load_model(tokenizer)
             if nlp.config["nlp"]["tokenizer"] == base_nlp.config["nlp"]["tokenizer"]:
                 nlp.tokenizer.from_bytes(base_nlp.tokenizer.to_bytes(exclude=["vocab"]))
@@ -23,7 +23,7 @@ def create_copy_from_base_model(
                     )
                 )
         if vocab:
-            logger.info(f"Copying vocab from: {vocab}")
+            logger.info("Copying vocab from: %s", vocab)
             # only reload if the vocab is from a different model
             if tokenizer != vocab:
                 base_nlp = load_model(vocab)

spacy/training/corpus.py

@@ -29,7 +29,7 @@ def create_docbin_reader(
 ) -> Callable[["Language"], Iterable[Example]]:
     if path is None:
         raise ValueError(Errors.E913)
-    util.logger.debug(f"Loading corpus from path: {path}")
+    util.logger.debug("Loading corpus from path: %s", path)
     return Corpus(
         path,
         gold_preproc=gold_preproc,
@@ -58,6 +58,28 @@ def read_labels(path: Path, *, require: bool = False):
     return srsly.read_json(path)
 
 
+@util.registry.readers("spacy.PlainTextCorpus.v1")
+def create_plain_text_reader(
+    path: Optional[Path],
+    min_length: int = 0,
+    max_length: int = 0,
+) -> Callable[["Language"], Iterable[Doc]]:
+    """Iterate Example objects from a file or directory of plain text
+    UTF-8 files with one line per doc.
+
+    path (Path): The directory or filename to read from.
+    min_length (int): Minimum document length (in tokens). Shorter documents
+        will be skipped. Defaults to 0, which indicates no limit.
+    max_length (int): Maximum document length (in tokens). Longer documents will
+        be skipped. Defaults to 0, which indicates no limit.
+
+    DOCS: https://spacy.io/api/corpus#plaintextcorpus
+    """
+    if path is None:
+        raise ValueError(Errors.E913)
+    return PlainTextCorpus(path, min_length=min_length, max_length=max_length)
+
+
 def walk_corpus(path: Union[str, Path], file_type) -> List[Path]:
     path = util.ensure_path(path)
     if not path.is_dir() and path.parts[-1].endswith(file_type):
@@ -257,3 +279,52 @@ class JsonlCorpus:
                     # We don't *need* an example here, but it seems nice to
                     # make it match the Corpus signature.
                     yield Example(doc, Doc(nlp.vocab, words=words, spaces=spaces))
+
+
+class PlainTextCorpus:
+    """Iterate Example objects from a file or directory of plain text
+    UTF-8 files with one line per doc.
+
+    path (Path): The directory or filename to read from.
+    min_length (int): Minimum document length (in tokens). Shorter documents
+        will be skipped. Defaults to 0, which indicates no limit.
+    max_length (int): Maximum document length (in tokens). Longer documents will
+        be skipped. Defaults to 0, which indicates no limit.
+
+    DOCS: https://spacy.io/api/corpus#plaintextcorpus
+    """
+
+    file_type = "txt"
+
+    def __init__(
+        self,
+        path: Optional[Union[str, Path]],
+        *,
+        min_length: int = 0,
+        max_length: int = 0,
+    ) -> None:
+        self.path = util.ensure_path(path)
+        self.min_length = min_length
+        self.max_length = max_length
+
+    def __call__(self, nlp: "Language") -> Iterator[Example]:
+        """Yield examples from the data.
+
+        nlp (Language): The current nlp object.
+        YIELDS (Example): The example objects.
+
+        DOCS: https://spacy.io/api/corpus#plaintextcorpus-call
+        """
+        for loc in walk_corpus(self.path, ".txt"):
+            with open(loc, encoding="utf-8") as f:
+                for text in f:
+                    text = text.rstrip("\r\n")
+                    if len(text):
+                        doc = nlp.make_doc(text)
+                        if self.min_length >= 1 and len(doc) < self.min_length:
+                            continue
+                        elif self.max_length >= 1 and len(doc) > self.max_length:
+                            continue
+                        # We don't *need* an example here, but it seems nice to
+                        # make it match the Corpus signature.
+                        yield Example(doc, doc.copy())

spacy/training/initialize.py

@@ -62,10 +62,10 @@ def init_nlp(config: Config, *, use_gpu: int = -1) -> "Language":
     frozen_components = T["frozen_components"]
     # Sourced components that require resume_training
     resume_components = [p for p in sourced if p not in frozen_components]
-    logger.info(f"Pipeline: {nlp.pipe_names}")
+    logger.info("Pipeline: %s", nlp.pipe_names)
     if resume_components:
         with nlp.select_pipes(enable=resume_components):
-            logger.info(f"Resuming training for: {resume_components}")
+            logger.info("Resuming training for: %s", resume_components)
             nlp.resume_training(sgd=optimizer)
     # Make sure that listeners are defined before initializing further
     nlp._link_components()
@@ -73,16 +73,17 @@ def init_nlp(config: Config, *, use_gpu: int = -1) -> "Language":
         if T["max_epochs"] == -1:
             sample_size = 100
             logger.debug(
-                f"Due to streamed train corpus, using only first {sample_size} "
+                "Due to streamed train corpus, using only first %s examples for initialization. "
-                f"examples for initialization. If necessary, provide all labels "
+                "If necessary, provide all labels in [initialize]. "
-                f"in [initialize]. More info: https://spacy.io/api/cli#init_labels"
+                "More info: https://spacy.io/api/cli#init_labels",
+                sample_size,
             )
             nlp.initialize(
                 lambda: islice(train_corpus(nlp), sample_size), sgd=optimizer
             )
         else:
             nlp.initialize(lambda: train_corpus(nlp), sgd=optimizer)
-        logger.info(f"Initialized pipeline components: {nlp.pipe_names}")
+        logger.info("Initialized pipeline components: %s", nlp.pipe_names)
     # Detect components with listeners that are not frozen consistently
     for name, proc in nlp.pipeline:
         for listener in getattr(
@@ -109,7 +110,7 @@ def init_vocab(
 ) -> None:
     if lookups:
         nlp.vocab.lookups = lookups
-        logger.info(f"Added vocab lookups: {', '.join(lookups.tables)}")
+        logger.info("Added vocab lookups: %s", ", ".join(lookups.tables))
     data_path = ensure_path(data)
     if data_path is not None:
         lex_attrs = srsly.read_jsonl(data_path)
@@ -125,11 +126,11 @@ def init_vocab(
         else:
             oov_prob = DEFAULT_OOV_PROB
         nlp.vocab.cfg.update({"oov_prob": oov_prob})
-        logger.info(f"Added {len(nlp.vocab)} lexical entries to the vocab")
+        logger.info("Added %d lexical entries to the vocab", len(nlp.vocab))
     logger.info("Created vocabulary")
     if vectors is not None:
         load_vectors_into_model(nlp, vectors)
-        logger.info(f"Added vectors: {vectors}")
+        logger.info("Added vectors: %s", vectors)
     # warn if source model vectors are not identical
     sourced_vectors_hashes = nlp.meta.pop("_sourced_vectors_hashes", {})
     vectors_hash = hash(nlp.vocab.vectors.to_bytes(exclude=["strings"]))
@@ -191,7 +192,7 @@ def init_tok2vec(
     if weights_data is not None:
         layer = get_tok2vec_ref(nlp, P)
         layer.from_bytes(weights_data)
-        logger.info(f"Loaded pretrained weights from {init_tok2vec}")
+        logger.info("Loaded pretrained weights from %s", init_tok2vec)
         return True
     return False
 
@@ -216,13 +217,13 @@ def convert_vectors(
         nlp.vocab.deduplicate_vectors()
     else:
         if vectors_loc:
-            logger.info(f"Reading vectors from {vectors_loc}")
+            logger.info("Reading vectors from %s", vectors_loc)
             vectors_data, vector_keys, floret_settings = read_vectors(
                 vectors_loc,
                 truncate,
                 mode=mode,
             )
-            logger.info(f"Loaded vectors from {vectors_loc}")
+            logger.info("Loaded vectors from %s", vectors_loc)
         else:
             vectors_data, vector_keys = (None, None)
         if vector_keys is not None and mode != VectorsMode.floret:

spacy/training/loop.py

@@ -370,6 +370,6 @@ def clean_output_dir(path: Optional[Path]) -> None:
             if subdir.exists():
                 try:
                     shutil.rmtree(str(subdir))
-                    logger.debug(f"Removed existing output directory: {subdir}")
+                    logger.debug("Removed existing output directory: %s", subdir)
                 except Exception as e:
                     raise IOError(Errors.E901.format(path=path)) from e

website/.dockerignore

@@ -0,0 +1,9 @@
+.cache/
+.next/
+public/
+node_modules
+.npm
+logs
+*.log
+npm-debug.log*
+quickstart-training-generator.js

website/.gitignore

@@ -1,5 +1,7 @@
 # See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
 
+quickstart-training-generator.js
+
 # dependencies
 /node_modules
 /.pnp
@@ -41,4 +43,4 @@ next-env.d.ts
 public/robots.txt
 public/sitemap*
 public/sw.js*
-public/workbox*
+public/workbox*

website/Dockerfile

@@ -1,16 +1,14 @@
-FROM node:11.15.0 
+FROM node:18
 
-WORKDIR /spacy-io
+USER node
-
-RUN npm install -g gatsby-cli@2.7.4
-
-COPY package.json .
-COPY package-lock.json . 
-
-RUN npm install
 
 # This is so the installed node_modules will be up one directory
 # from where a user mounts files, so that they don't accidentally mount
 # their own node_modules from a different build
 # https://nodejs.org/api/modules.html#modules_loading_from_node_modules_folders
-WORKDIR /spacy-io/website/
+WORKDIR /home/node
+COPY --chown=node package.json .
+COPY --chown=node package-lock.json .
+RUN npm install
+
+WORKDIR /home/node/website/

website/README.md

@@ -41,33 +41,27 @@ If you'd like to do this, **be sure you do _not_ include your local
 `node_modules` folder**, since there are some dependencies that need to be built
 for the image system. Rename it before using.
 
-```bash
+First build the Docker image. This only needs to be done on the first run
-docker run -it \
+or when changes are made to `Dockerfile` or the website dependencies:
-  -v $(pwd):/spacy-io/website \
-  -p 8000:8000 \
-  ghcr.io/explosion/spacy-io \
-  gatsby develop -H 0.0.0.0
-```
-
-This will allow you to access the built website at http://0.0.0.0:8000/ in your
-browser, and still edit code in your editor while having the site reflect those
-changes.
-
-**Note**: If you're working on a Mac with an M1 processor, you might see
-segfault errors from `qemu` if you use the default image. To fix this use the
-`arm64` tagged image in the `docker run` command
-(ghcr.io/explosion/spacy-io:arm64).
-
-### Building the Docker image
-
-If you'd like to build the image locally, you can do so like this:
 
 ```bash
 docker build -t spacy-io .
 ```
 
-This will take some time, so if you want to use the prebuilt image you'll save a
+You can then build and run the website with:
-bit of time.
+
+```bash
+docker run -it \
+  --rm \
+  -v $(pwd):/home/node/website \
+  -p 3000:3000 \
+  spacy-io \
+  npm run dev -- -H 0.0.0.0
+```
+
+This will allow you to access the built website at http://0.0.0.0:3000/ in your
+browser, and still edit code in your editor while having the site reflect those
+changes.
 
 ## Project structure
 

website/docs/api/cli.mdx

@@ -14,6 +14,7 @@ menu:
   - ['train', 'train']
   - ['pretrain', 'pretrain']
   - ['evaluate', 'evaluate']
+  - ['benchmark', 'benchmark']
   - ['apply', 'apply']
   - ['find-threshold', 'find-threshold']
   - ['assemble', 'assemble']
@@ -361,10 +362,10 @@ $ python -m spacy convert [input_file] [output_dir] [--converter] [--file-type]
 | `--file-type`, `-t`       | Type of file to create. Either `spacy` (default) for binary [`DocBin`](/api/docbin) data or `json` for v2.x JSON format. ~~str (option)~~ |
 | `--n-sents`, `-n`         | Number of sentences per document. Supported for: `conll`, `conllu`, `iob`, `ner` ~~int (option)~~                                         |
 | `--seg-sents`, `-s`       | Segment sentences. Supported for: `conll`, `ner` ~~bool (flag)~~                                                                          |
-| `--base`, `-b`, `--model` | Trained spaCy pipeline for sentence segmentation to use as base (for `--seg-sents`). ~~Optional[str](option)~~                            |
+| `--base`, `-b`, `--model` | Trained spaCy pipeline for sentence segmentation to use as base (for `--seg-sents`). ~~Optional[str] (option)~~                           |
 | `--morphology`, `-m`      | Enable appending morphology to tags. Supported for: `conllu` ~~bool (flag)~~                                                              |
 | `--merge-subtokens`, `-T` | Merge CoNLL-U subtokens ~~bool (flag)~~                                                                                                   |
-| `--ner-map`, `-nm`        | NER tag mapping (as JSON-encoded dict of entity types). Supported for: `conllu` ~~Optional[Path](option)~~                                |
+| `--ner-map`, `-nm`        | NER tag mapping (as JSON-encoded dict of entity types). Supported for: `conllu` ~~Optional[Path] (option)~~                               |
 | `--lang`, `-l`            | Language code (if tokenizer required). ~~Optional[str] \(option)~~                                                                        |
 | `--concatenate`, `-C`     | Concatenate output to a single file ~~bool (flag)~~                                                                                       |
 | `--help`, `-h`            | Show help message and available arguments. ~~bool (flag)~~                                                                                |
@@ -1227,8 +1228,19 @@ $ python -m spacy pretrain [config_path] [output_dir] [--code] [--resume-path] [
 
 ## evaluate {id="evaluate",version="2",tag="command"}
 
-Evaluate a trained pipeline. Expects a loadable spaCy pipeline (package name or
+The `evaluate` subcommand is superseded by
-path) and evaluation data in the
+[`spacy benchmark accuracy`](#benchmark-accuracy). `evaluate` is provided as an
+alias to `benchmark accuracy` for compatibility.
+
+## benchmark {id="benchmark", version="3.5"}
+
+The `spacy benchmark` CLI includes commands for benchmarking the accuracy and
+speed of your spaCy pipelines.
+
+### accuracy {id="benchmark-accuracy", version="3.5", tag="command"}
+
+Evaluate the accuracy of a trained pipeline. Expects a loadable spaCy pipeline
+(package name or path) and evaluation data in the
 [binary `.spacy` format](/api/data-formats#binary-training). The
 `--gold-preproc` option sets up the evaluation examples with gold-standard
 sentences and tokens for the predictions. Gold preprocessing helps the
@@ -1239,7 +1251,7 @@ skew. To render a sample of dependency parses in a HTML file using the
 `--displacy-path` argument.
 
 ```bash
-$ python -m spacy evaluate [model] [data_path] [--output] [--code] [--gold-preproc] [--gpu-id] [--displacy-path] [--displacy-limit]
+$ python -m spacy benchmark accuracy [model] [data_path] [--output] [--code] [--gold-preproc] [--gpu-id] [--displacy-path] [--displacy-limit]
 ```
 
 | Name                                      | Description                                                                                                                                                                          |
@@ -1255,6 +1267,29 @@ $ python -m spacy evaluate [model] [data_path] [--output] [--code] [--gold-prepr
 | `--help`, `-h`                            | Show help message and available arguments. ~~bool (flag)~~                                                                                                                           |
 | **CREATES**                               | Training results and optional metrics and visualizations.                                                                                                                            |
 
+### speed {id="benchmark-speed", version="3.5", tag="command"}
+
+Benchmark the speed of a trained pipeline with a 95% confidence interval.
+Expects a loadable spaCy pipeline (package name or path) and benchmark data in
+the [binary `.spacy` format](/api/data-formats#binary-training). The pipeline is
+warmed up before any measurements are taken.
+
+```cli
+$ python -m spacy benchmark speed [model] [data_path] [--batch_size] [--no-shuffle] [--gpu-id] [--batches] [--warmup]
+```
+
+| Name                 | Description                                                                                              |
+| -------------------- | -------------------------------------------------------------------------------------------------------- |
+| `model`              | Pipeline to benchmark the speed of. Can be a package or a path to a data directory. ~~str (positional)~~ |
+| `data_path`          | Location of benchmark data in spaCy's [binary format](/api/data-formats#training). ~~Path (positional)~~ |
+| `--batch-size`, `-b` | Set the batch size. If not set, the pipeline's batch size is used. ~~Optional[int] \(option)~~           |
+| `--no-shuffle`       | Do not shuffle documents in the benchmark data. ~~bool (flag)~~                                          |
+| `--gpu-id`, `-g`     | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~                                           |
+| `--batches`          | Number of batches to benchmark on. Defaults to `50`. ~~Optional[int] \(option)~~                         |
+| `--warmup`, `-w`     | Iterations over the benchmark data for warmup. Defaults to `3` ~~Optional[int] \(option)~~               |
+| `--help`, `-h`       | Show help message and available arguments. ~~bool (flag)~~                                               |
+| **PRINTS**           | Pipeline speed in words per second with a 95% confidence interval.                                       |
+
 ## apply {id="apply", version="3.5", tag="command"}
 
 Applies a trained pipeline to data and stores the resulting annotated documents
@@ -1268,23 +1303,23 @@ input formats are:
 
 When a directory is provided it is traversed recursively to collect all files.
 
-```cli
+```bash
 $ python -m spacy apply [model] [data-path] [output-file] [--code] [--text-key] [--force-overwrite] [--gpu-id] [--batch-size] [--n-process]
 ```
 
-| Name                                      | Description                                                                                                                                                                          |
+| Name                      | Description                                                                                                                                                                          |
-| ----------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `model`                                   | Pipeline to apply to the data. Can be a package or a path to a data directory. ~~str (positional)~~                                                                                  |
+| `model`                   | Pipeline to apply to the data. Can be a package or a path to a data directory. ~~str (positional)~~                                                                                  |
-| `data_path`                               | Location of data to be evaluated in spaCy's [binary format](/api/data-formats#training), jsonl, or plain text. ~~Path (positional)~~                                                 |
+| `data_path`               | Location of data to be evaluated in spaCy's [binary format](/api/data-formats#training), jsonl, or plain text. ~~Path (positional)~~                                                 |
-| `output-file`, `-o`                       | Output `DocBin` path. ~~str (positional)~~                                                                                                                                           |
+| `output-file`, `-o`       | Output `DocBin` path. ~~str (positional)~~                                                                                                                                           |
-| `--code`, `-c` <Tag variant="new">3</Tag> | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ |
+| `--code`, `-c`            | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ |
-| `--text-key`, `-tk`                       | The key for `.jsonl` files to use to grab the texts from. Defaults to `text`. ~~Optional[str] \(option)~~                                                                            |
+| `--text-key`, `-tk`       | The key for `.jsonl` files to use to grab the texts from. Defaults to `text`. ~~Optional[str] \(option)~~                                                                            |
-| `--force-overwrite`, `-F`                 | If the provided `output-file` already exists, then force `apply` to overwrite it. If this is `False` (default) then quits with a warning instead. ~~bool (flag)~~                    |
+| `--force-overwrite`, `-F` | If the provided `output-file` already exists, then force `apply` to overwrite it. If this is `False` (default) then quits with a warning instead. ~~bool (flag)~~                    |
-| `--gpu-id`, `-g`                          | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~                                                                                                                       |
+| `--gpu-id`, `-g`          | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~                                                                                                                       |
-| `--batch-size`, `-b`                      | Batch size to use for prediction. Defaults to `1`. ~~int (option)~~                                                                                                                  |
+| `--batch-size`, `-b`      | Batch size to use for prediction. Defaults to `1`. ~~int (option)~~                                                                                                                  |
-| `--n-process`, `-n`                       | Number of processes to use for prediction. Defaults to `1`. ~~int (option)~~                                                                                                         |
+| `--n-process`, `-n`       | Number of processes to use for prediction. Defaults to `1`. ~~int (option)~~                                                                                                         |
-| `--help`, `-h`                            | Show help message and available arguments. ~~bool (flag)~~                                                                                                                           |
+| `--help`, `-h`            | Show help message and available arguments. ~~bool (flag)~~                                                                                                                           |
-| **CREATES**                               | A `DocBin` with the annotations from the `model` for all the files found in `data-path`.                                                                                             |
+| **CREATES**               | A `DocBin` with the annotations from the `model` for all the files found in `data-path`.                                                                                             |
 
 ## find-threshold {id="find-threshold",version="3.5",tag="command"}
 
@@ -1467,12 +1502,13 @@ $ python -m spacy project assets [project_dir]
 > $ python -m spacy project assets [--sparse]
 > ```
 
-| Name             | Description                                                                                                                                               |
+| Name                                           | Description                                                                                                                                               |
-| ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ---------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `project_dir`    | Path to project directory. Defaults to current working directory. ~~Path (positional)~~                                                                   |
+| `project_dir`                                  | Path to project directory. Defaults to current working directory. ~~Path (positional)~~                                                                   |
-| `--sparse`, `-S` | Enable [sparse checkout](https://git-scm.com/docs/git-sparse-checkout) to only check out and download what's needed. Requires Git v22.2+. ~~bool (flag)~~ |
+| `--extra`, `-e` <Tag variant="new">3.3.1</Tag> | Download assets marked as "extra". Default false. ~~bool (flag)~~                                                                                         |
-| `--help`, `-h`   | Show help message and available arguments. ~~bool (flag)~~                                                                                                |
+| `--sparse`, `-S`                               | Enable [sparse checkout](https://git-scm.com/docs/git-sparse-checkout) to only check out and download what's needed. Requires Git v22.2+. ~~bool (flag)~~ |
-| **CREATES**      | Downloaded or copied assets defined in the `project.yml`.                                                                                                 |
+| `--help`, `-h`                                 | Show help message and available arguments. ~~bool (flag)~~                                                                                                |
+| **CREATES**                                    | Downloaded or copied assets defined in the `project.yml`.                                                                                                 |
 
 ### project run {id="project-run",tag="command"}
 
@@ -1548,7 +1584,7 @@ $ python -m spacy project push [remote] [project_dir]
 ### project pull {id="project-pull",tag="command"}
 
 Download all files or directories listed as `outputs` for commands, unless they
-are not already present locally. When searching for files in the remote, `pull`
+are already present locally. When searching for files in the remote, `pull`
 won't just look at the output path, but will also consider the **command
 string** and the **hashes of the dependencies**. For instance, let's say you've
 previously pushed a checkpoint to the remote, but now you've changed some

website/docs/api/corpus.mdx

@@ -175,3 +175,68 @@ Yield examples from the data.
 | ---------- | -------------------------------------- |
 | `nlp`      | The current `nlp` object. ~~Language~~ |
 | **YIELDS** | The examples. ~~Example~~              |
+
+## PlainTextCorpus {id="plaintextcorpus",tag="class",version="3.5.1"}
+
+Iterate over documents from a plain text file. Can be used to read the raw text
+corpus for language model
+[pretraining](/usage/embeddings-transformers#pretraining). The expected file
+format is:
+
+- UTF-8 encoding
+- One document per line
+- Blank lines are ignored.
+
+```text {title="Example"}
+Can I ask where you work now and what you do, and if you enjoy it?
+They may just pull out of the Seattle market completely, at least until they have autonomous vehicles.
+My cynical view on this is that it will never be free to the public. Reason: what would be the draw of joining the military? Right now their selling point is free Healthcare and Education. Ironically both are run horribly and most, that I've talked to, come out wishing they never went in.
+```
+
+### PlainTextCorpus.\_\_init\_\_ {id="plaintextcorpus-init",tag="method"}
+
+Initialize the reader.
+
+> #### Example
+>
+> ```python
+> from spacy.training import PlainTextCorpus
+>
+> corpus = PlainTextCorpus("./data/docs.txt")
+> ```
+>
+> ```ini
+> ### Example config
+> [corpora.pretrain]
+> @readers = "spacy.PlainTextCorpus.v1"
+> path = "corpus/raw_text.txt"
+> min_length = 0
+> max_length = 0
+> ```
+
+| Name           | Description                                                                                                                |
+| -------------- | -------------------------------------------------------------------------------------------------------------------------- |
+| `path`         | The directory or filename to read from. Expects newline-delimited documents in UTF8 format. ~~Union[str, Path]~~           |
+| _keyword-only_ |                                                                                                                            |
+| `min_length`   | Minimum document length (in tokens). Shorter documents will be skipped. Defaults to `0`, which indicates no limit. ~~int~~ |
+| `max_length`   | Maximum document length (in tokens). Longer documents will be skipped. Defaults to `0`, which indicates no limit. ~~int~~  |
+
+### PlainTextCorpus.\_\_call\_\_ {id="plaintextcorpus-call",tag="method"}
+
+Yield examples from the data.
+
+> #### Example
+>
+> ```python
+> from spacy.training import PlainTextCorpus
+> import spacy
+>
+> corpus = PlainTextCorpus("./docs.txt")
+> nlp = spacy.blank("en")
+> data = corpus(nlp)
+> ```
+
+| Name       | Description                            |
+| ---------- | -------------------------------------- |
+| `nlp`      | The current `nlp` object. ~~Language~~ |
+| **YIELDS** | The examples. ~~Example~~              |

website/docs/api/doc.mdx

@@ -37,7 +37,7 @@ Construct a `Doc` object. The most common way to get a `Doc` object is via the
 | `words`                                  | A list of strings or integer hash values to add to the document as words. ~~Optional[List[Union[str,int]]]~~                                                                                            |
 | `spaces`                                 | A list of boolean values indicating whether each word has a subsequent space. Must have the same length as `words`, if specified. Defaults to a sequence of `True`. ~~Optional[List[bool]]~~            |
 | _keyword-only_                           |                                                                                                                                                                                                         |
-| `user\_data`                             | Optional extra data to attach to the Doc. ~~Dict~~                                                                                                                                                      |
+| `user_data`                              | Optional extra data to attach to the Doc. ~~Dict~~                                                                                                                                                      |
 | `tags` <Tag variant="new">3</Tag>        | A list of strings, of the same length as `words`, to assign as `token.tag` for each word. Defaults to `None`. ~~Optional[List[str]]~~                                                                   |
 | `pos` <Tag variant="new">3</Tag>         | A list of strings, of the same length as `words`, to assign as `token.pos` for each word. Defaults to `None`. ~~Optional[List[str]]~~                                                                   |
 | `morphs` <Tag variant="new">3</Tag>      | A list of strings, of the same length as `words`, to assign as `token.morph` for each word. Defaults to `None`. ~~Optional[List[str]]~~                                                                 |
@@ -209,15 +209,16 @@ alignment mode `"strict".
 > assert span.text == "New York"
 > ```
 
-| Name             | Description                                                                                                                                                                                                                                                                  |
+| Name                                     | Description                                                                                                                                                                                                                                                                  |
-| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ---------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `start`          | The index of the first character of the span. ~~int~~                                                                                                                                                                                                                        |
+| `start`                                  | The index of the first character of the span. ~~int~~                                                                                                                                                                                                                        |
-| `end`            | The index of the last character after the span. ~~int~~                                                                                                                                                                                                                      |
+| `end`                                    | The index of the last character after the span. ~~int~~                                                                                                                                                                                                                      |
-| `label`          | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~                                                                                                                                                                                                  |
+| `label`                                  | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~                                                                                                                                                                                                  |
-| `kb_id`          | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~                                                                                                                                                                                    |
+| `kb_id`                                  | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~                                                                                                                                                                                    |
-| `vector`         | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~                                                                                                                                                                                               |
+| `vector`                                 | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~                                                                                                                                                                                               |
-| `alignment_mode` | How character indices snap to token boundaries. Options: `"strict"` (no snapping), `"contract"` (span of all tokens completely within the character span), `"expand"` (span of all tokens at least partially covered by the character span). Defaults to `"strict"`. ~~str~~ |
+| `alignment_mode`                         | How character indices snap to token boundaries. Options: `"strict"` (no snapping), `"contract"` (span of all tokens completely within the character span), `"expand"` (span of all tokens at least partially covered by the character span). Defaults to `"strict"`. ~~str~~ |
-| **RETURNS**      | The newly constructed object or `None`. ~~Optional[Span]~~                                                                                                                                                                                                                   |
+| `span_id` <Tag variant="new">3.3.1</Tag> | An identifier to associate with the span. ~~Union[int, str]~~                                                                                                                                                                                                                |
+| **RETURNS**                              | The newly constructed object or `None`. ~~Optional[Span]~~                                                                                                                                                                                                                   |
 
 ## Doc.set_ents {id="set_ents",tag="method",version="3"}
 

website/docs/api/entitylinker.mdx

@@ -15,7 +15,7 @@ world". It requires a `KnowledgeBase`, as well as a function to generate
 plausible candidates from that `KnowledgeBase` given a certain textual mention,
 and a machine learning model to pick the right candidate, given the local
 context of the mention. `EntityLinker` defaults to using the
-[`InMemoryLookupKB`](/api/kb_in_memory) implementation.
+[`InMemoryLookupKB`](/api/inmemorylookupkb) implementation.
 
 ## Assigned Attributes {id="assigned-attributes"}
 

website/docs/api/inmemorylookupkb.mdx

@@ -43,7 +43,7 @@ The length of the fixed-size entity vectors in the knowledge base.
 
 Add an entity to the knowledge base, specifying its corpus frequency and entity
 vector, which should be of length
-[`entity_vector_length`](/api/kb_in_memory#entity_vector_length).
+[`entity_vector_length`](/api/inmemorylookupkb#entity_vector_length).
 
 > #### Example
 >
@@ -79,8 +79,9 @@ frequency and entity vector for each entity.
 
 Add an alias or mention to the knowledge base, specifying its potential KB
 identifiers and their prior probabilities. The entity identifiers should refer
-to entities previously added with [`add_entity`](/api/kb_in_memory#add_entity)
+to entities previously added with
-or [`set_entities`](/api/kb_in_memory#set_entities). The sum of the prior
+[`add_entity`](/api/inmemorylookupkb#add_entity) or
+[`set_entities`](/api/inmemorylookupkb#set_entities). The sum of the prior
 probabilities should not exceed 1. Note that an empty string can not be used as
 alias.
 
@@ -156,7 +157,7 @@ Get a list of all aliases in the knowledge base.
 
 Given a certain textual mention as input, retrieve a list of candidate entities
 of type [`Candidate`](/api/kb#candidate). Wraps
-[`get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
+[`get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
 
 > #### Example
 >
@@ -174,7 +175,7 @@ of type [`Candidate`](/api/kb#candidate). Wraps
 
 ## InMemoryLookupKB.get_candidates_batch {id="get_candidates_batch",tag="method"}
 
-Same as [`get_candidates()`](/api/kb_in_memory#get_candidates), but for an
+Same as [`get_candidates()`](/api/inmemorylookupkb#get_candidates), but for an
 arbitrary number of mentions. The [`EntityLinker`](/api/entitylinker) component
 will call `get_candidates_batch()` instead of `get_candidates()`, if the config
 parameter `candidates_batch_size` is greater or equal than 1.
@@ -231,7 +232,7 @@ Given a certain entity ID, retrieve its pretrained entity vector.
 
 ## InMemoryLookupKB.get_vectors {id="get_vectors",tag="method"}
 
-Same as [`get_vector()`](/api/kb_in_memory#get_vector), but for an arbitrary
+Same as [`get_vector()`](/api/inmemorylookupkb#get_vector), but for an arbitrary
 number of entity IDs.
 
 The default implementation of `get_vectors()` executes `get_vector()` in a loop.

website/docs/api/kb.mdx

@@ -21,8 +21,8 @@ functions called by the [`EntityLinker`](/api/entitylinker) component.
 <Infobox variant="warning">
 
 This class was not abstract up to spaCy version 3.5. The `KnowledgeBase`
-implementation up to that point is available as `InMemoryLookupKB` from 3.5
+implementation up to that point is available as
-onwards.
+[`InMemoryLookupKB`](/api/inmemorylookupkb) from 3.5 onwards.
 
 </Infobox>
 
@@ -110,14 +110,15 @@ to you.
 </Infobox>
 
 From spaCy 3.5 on `KnowledgeBase` is an abstract class (with
-[`InMemoryLookupKB`](/api/kb_in_memory) being a drop-in replacement) to allow
+[`InMemoryLookupKB`](/api/inmemorylookupkb) being a drop-in replacement) to
-more flexibility in customizing knowledge bases. Some of its methods were moved
+allow more flexibility in customizing knowledge bases. Some of its methods were
-to [`InMemoryLookupKB`](/api/kb_in_memory) during this refactoring, one of those
+moved to [`InMemoryLookupKB`](/api/inmemorylookupkb) during this refactoring,
-being `get_alias_candidates()`. This method is now available as
+one of those being `get_alias_candidates()`. This method is now available as
-[`InMemoryLookupKB.get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
+[`InMemoryLookupKB.get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
-Note: [`InMemoryLookupKB.get_candidates()`](/api/kb_in_memory#get_candidates)
+Note:
+[`InMemoryLookupKB.get_candidates()`](/api/inmemorylookupkb#get_candidates)
 defaults to
-[`InMemoryLookupKB.get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates).
+[`InMemoryLookupKB.get_alias_candidates()`](/api/inmemorylookupkb#get_alias_candidates).
 
 ## KnowledgeBase.get_vector {id="get_vector",tag="method"}
 

website/docs/api/span.mdx

@@ -186,14 +186,17 @@ the character indices don't map to a valid span.
 > assert span.text == "New York"
 > ```
 
-| Name        | Description                                                                               |
+| Name                                            | Description                                                                                                                                                                                                                                                                  |
-| ----------- | ----------------------------------------------------------------------------------------- |
+| ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `start`     | The index of the first character of the span. ~~int~~                                     |
+| `start`                                         | The index of the first character of the span. ~~int~~                                                                                                                                                                                                                        |
-| `end`       | The index of the last character after the span. ~~int~~                                   |
+| `end`                                           | The index of the last character after the span. ~~int~~                                                                                                                                                                                                                      |
-| `label`     | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~               |
+| `label`                                         | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~                                                                                                                                                                                                  |
-| `kb_id`     | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ |
+| `kb_id`                                         | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~                                                                                                                                                                                    |
-| `vector`    | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~            |
+| `vector`                                        | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~                                                                                                                                                                                               |
-| **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~                                |
+| `id`                                            | Unused. ~~Union[int, str]~~                                                                                                                                                                                                                                                  |
+| `alignment_mode` <Tag variant="new">3.5.1</Tag> | How character indices snap to token boundaries. Options: `"strict"` (no snapping), `"contract"` (span of all tokens completely within the character span), `"expand"` (span of all tokens at least partially covered by the character span). Defaults to `"strict"`. ~~str~~ |
+| `span_id` <Tag variant="new">3.5.1</Tag>        | An identifier to associate with the span. ~~Union[int, str]~~                                                                                                                                                                                                                |
+| **RETURNS**                                     | The newly constructed object or `None`. ~~Optional[Span]~~                                                                                                                                                                                                                   |
 
 ## Span.similarity {id="similarity",tag="method",model="vectors"}
 

website/docs/api/top-level.mdx

@@ -236,17 +236,17 @@ browser. Will run a simple web server.
 > displacy.serve([doc1, doc2], style="dep")
 > ```
 
-| Name               | Description                                                                                                                                                       |
+| Name                                            | Description                                                                                                                                                       |
-| ------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `docs`             | Document(s) or span(s) to visualize. ~~Union[Iterable[Union[Doc, Span]], Doc, Span]~~                                                                             |
+| `docs`                                          | Document(s) or span(s) to visualize. ~~Union[Iterable[Union[Doc, Span]], Doc, Span]~~                                                                             |
-| `style`            | Visualization style, `"dep"`, `"ent"` or `"span"` <Tag variant="new">3.3</Tag>. Defaults to `"dep"`. ~~str~~                                                      |
+| `style` <Tag variant="new">3.3</Tag>            | Visualization style, `"dep"`, `"ent"` or `"span"`. Defaults to `"dep"`. ~~str~~                                                                                   |
-| `page`             | Render markup as full HTML page. Defaults to `True`. ~~bool~~                                                                                                     |
+| `page`                                          | Render markup as full HTML page. Defaults to `True`. ~~bool~~                                                                                                     |
-| `minify`           | Minify HTML markup. Defaults to `False`. ~~bool~~                                                                                                                 |
+| `minify`                                        | Minify HTML markup. Defaults to `False`. ~~bool~~                                                                                                                 |
-| `options`          | [Visualizer-specific options](#displacy_options), e.g. colors. ~~Dict[str, Any]~~                                                                                 |
+| `options`                                       | [Visualizer-specific options](#displacy_options), e.g. colors. ~~Dict[str, Any]~~                                                                                 |
-| `manual`           | Don't parse `Doc` and instead expect a dict or list of dicts. [See here](/usage/visualizers#manual-usage) for formats and examples. Defaults to `False`. ~~bool~~ |
+| `manual`                                        | Don't parse `Doc` and instead expect a dict or list of dicts. [See here](/usage/visualizers#manual-usage) for formats and examples. Defaults to `False`. ~~bool~~ |
-| `port`             | Port to serve visualization. Defaults to `5000`. ~~int~~                                                                                                          |
+| `port`                                          | Port to serve visualization. Defaults to `5000`. ~~int~~                                                                                                          |
-| `host`             | Host to serve visualization. Defaults to `"0.0.0.0"`. ~~str~~                                                                                                     |
+| `host`                                          | Host to serve visualization. Defaults to `"0.0.0.0"`. ~~str~~                                                                                                     |
-| `auto_select_port` | If `True`, automatically switch to a different port if the specified port is already in use. Defaults to `False`. ~~bool~~                                          |
+| `auto_select_port` <Tag variant="new">3.5</Tag> | If `True`, automatically switch to a different port if the specified port is already in use. Defaults to `False`. ~~bool~~                                        |
 
 ### displacy.render {id="displacy.render",tag="method",version="2"}
 

website/docs/models/index.mdx

@@ -21,8 +21,8 @@ menu:
 ## Package naming conventions {id="conventions"}
 
 In general, spaCy expects all pipeline packages to follow the naming convention
-of `[lang]\_[name]`. For spaCy's pipelines, we also chose to divide the name
+of `[lang]_[name]`. For spaCy's pipelines, we also chose to divide the name into
-into three components:
+three components:
 
 1. **Type:** Capabilities (e.g. `core` for general-purpose pipeline with
    tagging, parsing, lemmatization and named entity recognition, or `dep` for

website/docs/usage/101/_architecture.mdx

@@ -79,7 +79,7 @@ operates on a `Doc` and gives you access to the matched tokens **in context**.
 | ------------------------------------------------ | -------------------------------------------------------------------------------------------------- |
 | [`Corpus`](/api/corpus)                          | Class for managing annotated corpora for training and evaluation data.                             |
 | [`KnowledgeBase`](/api/kb)                       | Abstract base class for storage and retrieval of data for entity linking.                          |
-| [`InMemoryLookupKB`](/api/kb_in_memory)          | Implementation of `KnowledgeBase` storing all data in memory.                                      |
+| [`InMemoryLookupKB`](/api/inmemorylookupkb)      | Implementation of `KnowledgeBase` storing all data in memory.                                      |
 | [`Candidate`](/api/kb#candidate)                 | Object associating a textual mention with a specific entity contained in a `KnowledgeBase`.        |
 | [`Lookups`](/api/lookups)                        | Container for convenient access to large lookup tables and dictionaries.                           |
 | [`MorphAnalysis`](/api/morphology#morphanalysis) | A morphological analysis.                                                                          |

website/docs/usage/101/_vectors-similarity.mdx

@@ -134,6 +134,7 @@ useful for your purpose. Here are some important considerations to keep in mind:
 <Image
   src="/images/sense2vec.jpg"
   href="https://github.com/explosion/sense2vec"
+  alt="sense2vec Screenshot"
 />
 
 [`sense2vec`](https://github.com/explosion/sense2vec) is a library developed by

website/docs/usage/layers-architectures.mdx

@@ -113,6 +113,7 @@ code.
 <Image
   src="/images/thinc_mypy.jpg"
   href="https://thinc.ai/docs/usage-type-checking#linting"
+  alt="Screenshot of Thinc type checking in VSCode with mypy"
 />
 
 </Accordion>

website/docs/usage/projects.mdx

@@ -943,7 +943,7 @@ full embedded visualizer, as well as individual components.
 > $ pip install spacy-streamlit --pre
 > ```
 
-![](/images/spacy-streamlit.png)
+![Screenshot of the spacy-streamlit package in Streamlit](/images/spacy-streamlit.png)
 
 Using [`spacy-streamlit`](https://github.com/explosion/spacy-streamlit), your
 projects can easily define their own scripts that spin up an interactive

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

@@ -384,14 +384,14 @@ the more specific attributes `FUZZY1`..`FUZZY9` you can specify the maximum
 allowed edit distance directly.
 
 ```python
-# Match lowercase with fuzzy matching (allows 2 edits)
+# Match lowercase with fuzzy matching (allows 3 edits)
 pattern = [{"LOWER": {"FUZZY": "definitely"}}]
 
-# Match custom attribute values with fuzzy matching (allows 2 edits)
+# Match custom attribute values with fuzzy matching (allows 3 edits)
 pattern = [{"_": {"country": {"FUZZY": "Kyrgyzstan"}}}]
 
-# Match with exact Levenshtein edit distance limits (allows 3 edits)
+# Match with exact Levenshtein edit distance limits (allows 4 edits)
-pattern = [{"_": {"country": {"FUZZY3": "Kyrgyzstan"}}}]
+pattern = [{"_": {"country": {"FUZZY4": "Kyrgyzstan"}}}]
 ```
 
 #### Regex and fuzzy matching with lists {id="regex-fuzzy-lists", version="3.5"}
@@ -1442,8 +1442,8 @@ nlp.to_disk("/path/to/pipeline")
 
 The saved pipeline now includes the `"entity_ruler"` in its
 [`config.cfg`](/api/data-formats#config) and the pipeline directory contains a
-file `entityruler.jsonl` with the patterns. When you load the pipeline back in,
+file `patterns.jsonl` with the patterns. When you load the pipeline back in, all
-all pipeline components will be restored and deserialized – including the entity
+pipeline components will be restored and deserialized – including the entity
 ruler. This lets you ship powerful pipeline packages with binary weights _and_
 rules included!
 

website/docs/usage/saving-loading.mdx

@@ -304,6 +304,28 @@ installed in the same environment – that's it.
 | `spacy_lookups`                                   | Group of entry points for custom [`Lookups`](/api/lookups), including lemmatizer data. Used by spaCy's [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data) package.                                                                  |
 | [`spacy_displacy_colors`](#entry-points-displacy) | Group of entry points of custom label colors for the [displaCy visualizer](/usage/visualizers#ent). The key name doesn't matter, but it should point to a dict of labels and color values. Useful for custom models that predict different entity types. |
 
+### Loading probability tables into existing models
+
+You can load a probability table from [spacy-lookups-data](https://github.com/explosion/spacy-lookups-data) into an existing spaCy model like `en_core_web_sm`.
+
+```python
+# Requirements: pip install spacy-lookups-data
+import spacy
+from spacy.lookups import load_lookups
+nlp = spacy.load("en_core_web_sm")
+lookups = load_lookups("en", ["lexeme_prob"])
+nlp.vocab.lookups.add_table("lexeme_prob", lookups.get_table("lexeme_prob"))
+```
+
+When training a model from scratch you can also specify probability tables in the `config.cfg`.
+
+```ini {title="config.cfg (excerpt)"}
+[initialize.lookups]
+@misc = "spacy.LookupsDataLoader.v1"
+lang = ${nlp.lang}
+tables = ["lexeme_prob"]
+```
+
 ### Custom components via entry points {id="entry-points-components"}
 
 When you load a pipeline, spaCy will generally use its `config.cfg` to set up
@@ -684,10 +706,15 @@ If your pipeline includes
 [custom components](/usage/processing-pipelines#custom-components), model
 architectures or other [code](/usage/training#custom-code), those functions need
 to be registered **before** your pipeline is loaded. Otherwise, spaCy won't know
-how to create the objects referenced in the config. The
+how to create the objects referenced in the config. If you're loading your own
-[`spacy package`](/api/cli#package) command lets you provide one or more paths
+pipeline in Python, you can make custom components available just by importing
-to Python files containing custom registered functions using the `--code`
+the code that defines them before calling
-argument.
+[`spacy.load`](/api/top-level#spacy.load). This is also how the `--code`
+argument to CLI commands works.
+
+With the [`spacy package`](/api/cli#package) command, you can provide one or
+more paths to Python files containing custom registered functions using the
+`--code` argument.
 
 > #### \_\_init\_\_.py (excerpt)
 >

website/docs/usage/spacy-101.mdx

@@ -567,7 +567,10 @@ If you would like to use the spaCy logo on your site, please get in touch and
 ask us first. However, if you want to show support and tell others that your
 project is using spaCy, you can grab one of our **spaCy badges** here:
 
-<img src={`https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg`} />
+<img
+  src={`https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg`}
+  alt="Built with spaCy"
+/>
 
 ```markdown
 [![Built with spaCy](https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg)](https://spacy.io)
@@ -575,8 +578,9 @@ project is using spaCy, you can grab one of our **spaCy badges** here:
 
 <img
   src={`https://img.shields.io/badge/made%20with%20❤%20and-spaCy-09a3d5.svg`}
+  alt="Made with love and spaCy"
 />
 
 ```markdown
-[![Built with spaCy](https://img.shields.io/badge/made%20with%20❤%20and-spaCy-09a3d5.svg)](https://spacy.io)
+[![Made with love and spaCy](https://img.shields.io/badge/made%20with%20❤%20and-spaCy-09a3d5.svg)](https://spacy.io)
 ```

website/docs/usage/v3-5.mdx

@@ -0,0 +1,230 @@
+---
+title: What's New in v3.5
+teaser: New features and how to upgrade
+menu:
+  - ['New Features', 'features']
+  - ['Upgrading Notes', 'upgrading']
+---
+
+## New features {id="features",hidden="true"}
+
+spaCy v3.5 introduces three new CLI commands, `apply`, `benchmark` and
+`find-threshold`, adds fuzzy matching, provides improvements to our entity
+linking functionality, and includes a range of language updates and bug fixes.
+
+### New CLI commands {id="cli"}
+
+#### apply CLI
+
+The [`apply` CLI](/api/cli#apply) can be used to apply a pipeline to one or more
+`.txt`, `.jsonl` or `.spacy` input files, saving the annotated docs in a single
+`.spacy` file.
+
+```bash
+$ spacy apply en_core_web_sm my_texts/ output.spacy
+```
+
+#### benchmark CLI
+
+The [`benchmark` CLI](/api/cli#benchmark) has been added to extend the existing
+`evaluate` functionality with a wider range of profiling subcommands.
+
+The `benchmark accuracy` CLI is introduced as an alias for `evaluate`. The new
+`benchmark speed` CLI performs warmup rounds before measuring the speed in words
+per second on batches of randomly shuffled documents from the provided data.
+
+```bash
+$ spacy benchmark speed my_pipeline data.spacy
+```
+
+The output is the mean performance using batches (`nlp.pipe`) with a 95%
+confidence interval, e.g., profiling `en_core_web_sm` on CPU:
+
+```none
+Outliers: 2.0%, extreme outliers: 0.0%
+Mean: 18904.1 words/s (95% CI: -256.9 +244.1)
+```
+
+#### find-threshold CLI
+
+The [`find-threshold` CLI](/api/cli#find-threshold) runs a series of trials
+across threshold values from `0.0` to `1.0` and identifies the best threshold
+for the provided score metric.
+
+The following command runs 20 trials for the `spancat` component in
+`my_pipeline`, recording the `spans_sc_f` score for each value of the threshold
+`[components.spancat.threshold]` from `0.0` to `1.0`:
+
+```bash
+$ spacy find-threshold my_pipeline data.spacy spancat threshold spans_sc_f --n_trials 20
+```
+
+The `find-threshold` CLI can be used with `textcat_multilabel`, `spancat` and
+custom components with thresholds that are applied while predicting or scoring.
+
+### Fuzzy matching {id="fuzzy"}
+
+New `FUZZY` operators support [fuzzy matching](/usage/rule-based-matching#fuzzy)
+with the `Matcher`. By default, the `FUZZY` operator allows a Levenshtein edit
+distance of 2 and up to 30% of the pattern string length. `FUZZY1`..`FUZZY9` can
+be used to specify the exact number of allowed edits.
+
+```python
+# Match lowercase with fuzzy matching (allows up to 3 edits)
+pattern = [{"LOWER": {"FUZZY": "definitely"}}]
+
+# Match custom attribute values with fuzzy matching (allows up to 3 edits)
+pattern = [{"_": {"country": {"FUZZY": "Kyrgyzstan"}}}]
+
+# Match with exact Levenshtein edit distance limits (allows up to 4 edits)
+pattern = [{"_": {"country": {"FUZZY4": "Kyrgyzstan"}}}]
+```
+
+Note that `FUZZY` uses Levenshtein edit distance rather than Damerau-Levenshtein
+edit distance, so a transposition like `teh` for `the` counts as two edits, one
+insertion and one deletion.
+
+If you'd prefer an alternate fuzzy matching algorithm, you can provide your own
+custom method to the `Matcher` or as a config option for an entity ruler and
+span ruler.
+
+### FUZZY and REGEX with lists {id="fuzzy-regex-lists"}
+
+The `FUZZY` and `REGEX` operators are also now supported for lists with `IN` and
+`NOT_IN`:
+
+```python
+pattern = [{"TEXT": {"FUZZY": {"IN": ["awesome", "cool", "wonderful"]}}}]
+pattern = [{"TEXT": {"REGEX": {"NOT_IN": ["^awe(some)?$", "^wonder(ful)?"]}}}]
+```
+
+### Entity linking generalization {id="el"}
+
+The knowledge base used for entity linking is now easier to customize and has a
+new default implementation [`InMemoryLookupKB`](/api/inmemorylookupkb).
+
+### Additional features and improvements {id="additional-features-and-improvements"}
+
+- Language updates:
+  - Extended support for Slovenian
+  - Fixed lookup fallback for French and Catalan lemmatizers
+  - Switch Russian and Ukrainian lemmatizers to `pymorphy3`
+  - Support for editorial punctuation in Ancient Greek
+  - Update to Russian tokenizer exceptions
+  - Small fix for Dutch stop words
+- Allow up to `typer` v0.7.x, `mypy` 0.990 and `typing_extensions` v4.4.x.
+- New `spacy.ConsoleLogger.v3` with expanded progress
+  [tracking](/api/top-level#ConsoleLogger).
+- Improved scoring behavior for `textcat` with `spacy.textcat_scorer.v2` and
+  `spacy.textcat_multilabel_scorer.v2`.
+- Updates so that downstream components can train properly on a frozen `tok2vec`
+  or `transformer` layer.
+- Allow interpolation of variables in directory names in projects.
+- Support for local file system [remotes](/usage/projects#remote) for projects.
+- Improve UX around `displacy.serve` when the default port is in use.
+- Optional `before_update` callback that is invoked at the start of each
+  [training step](/api/data-formats#config-training).
+- Improve performance of `SpanGroup` and fix typing issues for `SpanGroup` and
+  `Span` objects.
+- Patch a
+  [security vulnerability](https://github.com/advisories/GHSA-gw9q-c7gh-j9vm) in
+  extracting tar files.
+- Add equality definition for `Vectors`.
+- Ensure `Vocab.to_disk` respects the exclude setting for `lookups` and
+  `vectors`.
+- Correctly handle missing annotations in the edit tree lemmatizer.
+
+### Trained pipeline updates {id="pipelines"}
+
+- The CNN pipelines add `IS_SPACE` as a `tok2vec` feature for `tagger` and
+  `morphologizer` components to improve tagging of non-whitespace vs. whitespace
+  tokens.
+- The transformer pipelines require `spacy-transformers` v1.2, which uses the
+  exact alignment from `tokenizers` for fast tokenizers instead of the heuristic
+  alignment from `spacy-alignments`. For all trained pipelines except
+  `ja_core_news_trf`, the alignments between spaCy tokens and transformer tokens
+  may be slightly different. More details about the `spacy-transformers` changes
+  in the
+  [v1.2.0 release notes](https://github.com/explosion/spacy-transformers/releases/tag/v1.2.0).
+
+## Notes about upgrading from v3.4 {id="upgrading"}
+
+### Validation of textcat values {id="textcat-validation"}
+
+An error is now raised when unsupported values are given as input to train a
+`textcat` or `textcat_multilabel` model - ensure that values are `0.0` or `1.0`
+as explained in the [docs](/api/textcategorizer#assigned-attributes).
+
+### Using the default knowledge base
+
+As `KnowledgeBase` is now an abstract class, you should call the constructor of
+the new `InMemoryLookupKB` instead when you want to use spaCy's default KB
+implementation:
+
+```diff
+- kb = KnowledgeBase()
++ kb = InMemoryLookupKB()
+```
+
+If you've written a custom KB that inherits from `KnowledgeBase`, you'll need to
+implement its abstract methods, or alternatively inherit from `InMemoryLookupKB`
+instead.
+
+### Updated scorers for tokenization and textcat {id="scores"}
+
+We fixed a bug that inflated the `token_acc` scores in v3.0-v3.4. The reported
+`token_acc` will drop from v3.4 to v3.5, but if `token_p/r/f` stay the same,
+your tokenization performance has not changed from v3.4.
+
+For new `textcat` or `textcat_multilabel` configs, the new default `v2` scorers:
+
+- ignore `threshold` for `textcat`, so the reported `cats_p/r/f` may increase
+  slightly in v3.5 even though the underlying predictions are unchanged
+- report the performance of only the **final** `textcat` or `textcat_multilabel`
+  component in the pipeline by default
+- allow custom scorers to be used to score multiple `textcat` and
+  `textcat_multilabel` components with `Scorer.score_cats` by restricting the
+  evaluation to the component's provided labels
+
+### Pipeline package version compatibility {id="version-compat"}
+
+> #### Using legacy implementations
+>
+> In spaCy v3, you'll still be able to load and reference legacy implementations
+> via [`spacy-legacy`](https://github.com/explosion/spacy-legacy), even if the
+> components or architectures change and newer versions are available in the
+> core library.
+
+When you're loading a pipeline package trained with an earlier version of spaCy
+v3, you will see a warning telling you that the pipeline may be incompatible.
+This doesn't necessarily have to be true, but we recommend running your
+pipelines against your test suite or evaluation data to make sure there are no
+unexpected results.
+
+If you're using one of the [trained pipelines](/models) we provide, you should
+run [`spacy download`](/api/cli#download) to update to the latest version. To
+see an overview of all installed packages and their compatibility, you can run
+[`spacy validate`](/api/cli#validate).
+
+If you've trained your own custom pipeline and you've confirmed that it's still
+working as expected, you can update the spaCy version requirements in the
+[`meta.json`](/api/data-formats#meta):
+
+```diff
+- "spacy_version": ">=3.4.0,<3.5.0",
++ "spacy_version": ">=3.4.0,<3.6.0",
+```
+
+### Updating v3.4 configs
+
+To update a config from spaCy v3.4 with the new v3.5 settings, run
+[`init fill-config`](/api/cli#init-fill-config):
+
+```cli
+$ python -m spacy init fill-config config-v3.4.cfg config-v3.5.cfg
+```
+
+In many cases ([`spacy train`](/api/cli#train),
+[`spacy.load`](/api/top-level#spacy.load)), the new defaults will be filled in
+automatically, but you'll need to fill in the new settings to run
+[`debug config`](/api/cli#debug) and [`debug data`](/api/cli#debug-data).

website/docs/usage/visualizers.mdx

@@ -437,6 +437,6 @@ Alternatively, if you're using [Streamlit](https://streamlit.io), check out the
 helps you integrate spaCy visualizations into your apps. It includes a full
 embedded visualizer, as well as individual components.
 
-![](/images/spacy-streamlit.png)
+![Screenshot of the spacy-streamlit package in Streamlit](/images/spacy-streamlit.png)
 
 </Grid>

website/meta/sidebars.json

@@ -13,7 +13,8 @@
                     { "text": "New in v3.1", "url": "/usage/v3-1" },
                     { "text": "New in v3.2", "url": "/usage/v3-2" },
                     { "text": "New in v3.3", "url": "/usage/v3-3" },
-                    { "text": "New in v3.4", "url": "/usage/v3-4" }
+                    { "text": "New in v3.4", "url": "/usage/v3-4" },
+                    { "text": "New in v3.5", "url": "/usage/v3-5" }
                 ]
             },
             {
@@ -129,6 +130,7 @@
                 "items": [
                     { "text": "Attributes", "url": "/api/attributes" },
                     { "text": "Corpus", "url": "/api/corpus" },
+                    { "text": "InMemoryLookupKB", "url": "/api/inmemorylookupkb" },
                     { "text": "KnowledgeBase", "url": "/api/kb" },
                     { "text": "Lookups", "url": "/api/lookups" },
                     { "text": "MorphAnalysis", "url": "/api/morphology#morphanalysis" },

website/meta/site.json

@@ -27,7 +27,7 @@
         "indexName": "spacy"
     },
     "binderUrl": "explosion/spacy-io-binder",
-    "binderVersion": "3.4",
+    "binderVersion": "3.5",
     "sections": [
         { "id": "usage", "title": "Usage Documentation", "theme": "blue" },
         { "id": "models", "title": "Models Documentation", "theme": "blue" },

website/meta/universe.json

@@ -2377,7 +2377,7 @@
             "author": "Nikita Kitaev",
             "author_links": {
                 "github": "nikitakit",
-                "website": " http://kitaev.io"
+                "website": "http://kitaev.io"
             },
             "category": ["research", "pipeline"]
         },

website/pages/_app.tsx

@@ -17,7 +17,7 @@ export default function App({ Component, pageProps }: AppProps) {
                 <link rel="manifest" href="/manifest.webmanifest" />
                 <meta
                     name="viewport"
-                    content="width=device-width, initial-scale=1.0, minimum-scale=1 maximum-scale=1.0, user-scalable=0, shrink-to-fit=no, viewport-fit=cover"
+                    content="width=device-width, initial-scale=1.0, minimum-scale=1, maximum-scale=5.0, shrink-to-fit=no, viewport-fit=cover"
                 />
                 <meta name="theme-color" content="#09a3d5" />
                 <link rel="apple-touch-icon" sizes="192x192" href="/icons/icon-192x192.png" />

website/pages/index.tsx

@@ -13,7 +13,7 @@ import {
     LandingBanner,
 } from '../src/components/landing'
 import { H2 } from '../src/components/typography'
-import { InlineCode } from '../src/components/code'
+import { InlineCode } from '../src/components/inlineCode'
 import { Ul, Li } from '../src/components/list'
 import Button from '../src/components/button'
 import Link from '../src/components/link'
@@ -89,8 +89,8 @@ const Landing = () => {
                 </LandingCard>
 
                 <LandingCard title="Awesome ecosystem" url="/usage/projects" button="Read more">
-                    In the five years since its release, spaCy has become an industry standard with
+                    Since its release in 2015, spaCy has become an industry standard with a huge
-                    a huge ecosystem. Choose from a variety of plugins, integrate with your machine
+                    ecosystem. Choose from a variety of plugins, integrate with your machine
                     learning stack and build custom components and workflows.
                 </LandingCard>
             </LandingGrid>
@@ -162,7 +162,7 @@ const Landing = () => {
                     small
                 >
                     <p>
-                        <Link to="https://prodi.gy" hidden>
+                        <Link to="https://prodi.gy" noLinkLayout>
                             <ImageFill
                                 image={prodigyImage}
                                 alt="Prodigy: Radically efficient machine teaching"
@@ -206,7 +206,10 @@ const Landing = () => {
             <LandingGrid cols={2}>
                 <LandingCol>
                     <Link to="/usage/projects" hidden>
-                        <ImageFill image={projectsImage} />
+                        <ImageFill
+                            image={projectsImage}
+                            alt="Illustration of project workflow and commands"
+                        />
                     </Link>
                     <br />
                     <br />

website/src/components/accordion.js

@@ -33,7 +33,7 @@ export default function Accordion({ title, id, expanded = false, spaced = false,
                                 <Link
                                     to={`#${id}`}
                                     className={classes.anchor}
-                                    hidden
+                                    noLinkLayout
                                     onClick={(event) => event.stopPropagation()}
                                 >
                                     &para;

website/src/components/card.js

@@ -1,6 +1,7 @@
 import React from 'react'
 import PropTypes from 'prop-types'
 import classNames from 'classnames'
+import ImageNext from 'next/image'
 
 import Link from './link'
 import { H5 } from './typography'
@@ -10,7 +11,7 @@ export default function Card({ title, to, image, header, small, onClick, childre
     return (
         <div className={classNames(classes.root, { [classes.small]: !!small })}>
             {header && (
-                <Link to={to} onClick={onClick} hidden>
+                <Link to={to} onClick={onClick} noLinkLayout>
                     {header}
                 </Link>
             )}
@@ -18,18 +19,17 @@ export default function Card({ title, to, image, header, small, onClick, childre
                 <H5 className={classes.title}>
                     {image && (
                         <div className={classes.image}>
-                            {/* eslint-disable-next-line @next/next/no-img-element */}
+                            <ImageNext src={image} height={35} width={35} alt={`${title} Logo`} />
-                            <img src={image} width={35} alt="" />
                         </div>
                     )}
                     {title && (
-                        <Link to={to} onClick={onClick} hidden>
+                        <Link to={to} onClick={onClick} noLinkLayout>
                             {title}
                         </Link>
                     )}
                 </H5>
             )}
-            <Link to={to} onClick={onClick} hidden>
+            <Link to={to} onClick={onClick} noLinkLayout>
                 {children}
             </Link>
         </div>

website/src/components/code.js

@@ -14,96 +14,16 @@ import 'prismjs/components/prism-markdown.min.js'
 import 'prismjs/components/prism-python.min.js'
 import 'prismjs/components/prism-yaml.min.js'
 
-import CUSTOM_TYPES from '../../meta/type-annotations.json'
+import { isString } from './util'
-import { isString, htmlToReact } from './util'
 import Link, { OptionalLink } from './link'
 import GitHubCode from './github'
-import Juniper from './juniper'
 import classes from '../styles/code.module.sass'
 import siteMetadata from '../../meta/site.json'
 import { binderBranch } from '../../meta/dynamicMeta.mjs'
+import dynamic from 'next/dynamic'
 
-const WRAP_THRESHOLD = 30
 const CLI_GROUPS = ['init', 'debug', 'project', 'ray', 'huggingface-hub']
 
-const CodeBlock = (props) => (
-    <Pre>
-        <Code {...props} />
-    </Pre>
-)
-
-export default CodeBlock
-
-export const Pre = (props) => {
-    return <pre className={classes['pre']}>{props.children}</pre>
-}
-
-export const InlineCode = ({ wrap = false, className, children, ...props }) => {
-    const codeClassNames = classNames(classes['inline-code'], className, {
-        [classes['wrap']]: wrap || (isString(children) && children.length >= WRAP_THRESHOLD),
-    })
-    return (
-        <code className={codeClassNames} {...props}>
-            {children}
-        </code>
-    )
-}
-
-InlineCode.propTypes = {
-    wrap: PropTypes.bool,
-    className: PropTypes.string,
-    children: PropTypes.node,
-}
-
-function linkType(el, showLink = true) {
-    if (!isString(el) || !el.length) return el
-    const elStr = el.trim()
-    if (!elStr) return el
-    const typeUrl = CUSTOM_TYPES[elStr]
-    const url = typeUrl == true ? DEFAULT_TYPE_URL : typeUrl
-    const ws = el[0] == ' '
-    return url && showLink ? (
-        <Fragment>
-            {ws && ' '}
-            <Link to={url} hideIcon>
-                {elStr}
-            </Link>
-        </Fragment>
-    ) : (
-        el
-    )
-}
-
-export const TypeAnnotation = ({ lang = 'python', link = true, children }) => {
-    // Hacky, but we're temporarily replacing a dot to prevent it from being split during highlighting
-    const TMP_DOT = '۔'
-    const code = Array.isArray(children) ? children.join('') : children || ''
-    const [rawText, meta] = code.split(/(?= \(.+\)$)/)
-    const rawStr = rawText.replace(/\./g, TMP_DOT)
-    const rawHtml =
-        lang === 'none' || !code ? code : Prism.highlight(rawStr, Prism.languages[lang], lang)
-    const html = rawHtml.replace(new RegExp(TMP_DOT, 'g'), '.').replace(/\n/g, ' ')
-    const result = htmlToReact(html)
-    const elements = Array.isArray(result) ? result : [result]
-    const annotClassNames = classNames(
-        'type-annotation',
-        `language-${lang}`,
-        classes['inline-code'],
-        classes['type-annotation'],
-        {
-            [classes['wrap']]: code.length >= WRAP_THRESHOLD,
-        }
-    )
-    return (
-        <span className={annotClassNames} role="code" aria-label="Type annotation">
-            {elements.map((el, i) => (
-                <Fragment key={i}>{linkType(el, !!link)}</Fragment>
-            ))}
-            {meta && <span className={classes['type-annotation-meta']}>{meta}</span>}
-        </span>
-    )
-}
-
 const splitLines = (children) => {
     const listChildrenPerLine = []
 
@@ -235,7 +155,7 @@ const handlePromot = ({ lineFlat, prompt }) => {
                     <Fragment key={j}>
                         {j !== 0 && ' '}
                         <span className={itemClassNames}>
-                            <OptionalLink hidden hideIcon to={url}>
+                            <OptionalLink noLinkLayout hideIcon to={url}>
                                 {text}
                             </OptionalLink>
                         </span>
@@ -288,7 +208,7 @@ const addLineHighlight = (children, highlight) => {
     })
 }
 
-export const CodeHighlighted = ({ children, highlight, lang }) => {
+const CodeHighlighted = ({ children, highlight, lang }) => {
     const [html, setHtml] = useState()
 
     useEffect(
@@ -305,7 +225,7 @@ export const CodeHighlighted = ({ children, highlight, lang }) => {
     return <>{html}</>
 }
 
-export class Code extends React.Component {
+export default class Code extends React.Component {
     static defaultProps = {
         lang: 'none',
         executable: null,
@@ -354,6 +274,8 @@ export class Code extends React.Component {
     }
 }
 
+const JuniperDynamic = dynamic(() => import('./juniper'))
+
 const JuniperWrapper = ({ title, lang, children }) => {
     const { binderUrl, binderVersion } = siteMetadata
     const juniperTitle = title || 'Editable Code'
@@ -363,13 +285,13 @@ const JuniperWrapper = ({ title, lang, children }) => {
                 {juniperTitle}
                 <span className={classes['juniper-meta']}>
                     spaCy v{binderVersion} &middot; Python 3 &middot; via{' '}
-                    <Link to="https://mybinder.org/" hidden>
+                    <Link to="https://mybinder.org/" noLinkLayout>
                         Binder
                     </Link>
                 </span>
             </h4>
 
-            <Juniper
+            <JuniperDynamic
                 repo={binderUrl}
                 branch={binderBranch}
                 lang={lang}
@@ -381,7 +303,7 @@ const JuniperWrapper = ({ title, lang, children }) => {
                 }}
             >
                 {children}
-            </Juniper>
+            </JuniperDynamic>
         </div>
     )
 }

website/src/components/codeBlock.js

@@ -0,0 +1,14 @@
+import React from 'react'
+import Code from './codeDynamic'
+import classes from '../styles/code.module.sass'
+
+export const Pre = (props) => {
+    return <pre className={classes['pre']}>{props.children}</pre>
+}
+
+const CodeBlock = (props) => (
+    <Pre>
+        <Code {...props} />
+    </Pre>
+)
+export default CodeBlock

website/src/components/codeDynamic.js

@@ -0,0 +1,5 @@
+import dynamic from 'next/dynamic'
+
+export default dynamic(() => import('./code'), {
+    loading: () => <div style={{ color: 'white', padding: '1rem' }}>Loading...</div>,
+})

website/src/components/copy.js

@@ -14,7 +14,7 @@ export function copyToClipboard(ref, callback) {
     }
 }
 
-export default function CopyInput({ text, prefix }) {
+export default function CopyInput({ text, description, prefix }) {
     const isClient = typeof window !== 'undefined'
     const [supportsCopy, setSupportsCopy] = useState(false)
 
@@ -41,6 +41,7 @@ export default function CopyInput({ text, prefix }) {
                 defaultValue={text}
                 rows={1}
                 onClick={selectText}
+                aria-label={description}
             />
             {supportsCopy && (
                 <button title="Copy to clipboard" onClick={onClick}>

website/src/components/embed.js

@@ -5,8 +5,8 @@ import ImageNext from 'next/image'
 
 import Link from './link'
 import Button from './button'
-import { InlineCode } from './code'
+import { InlineCode } from './inlineCode'
-import { MarkdownToReact } from './util'
+import MarkdownToReact from './markdownToReactDynamic'
 
 import classes from '../styles/embed.module.sass'
 
@@ -88,10 +88,16 @@ const Image = ({ src, alt, title, href, ...props }) => {
     const markdownComponents = { code: InlineCode, p: Fragment, a: Link }
     return (
         <figure className="gatsby-resp-image-figure">
-            <Link className={linkClassNames} href={href ?? src} hidden forceExternal>
+            {href ? (
-                {/* eslint-disable-next-line @next/next/no-img-element */}
+                <Link className={linkClassNames} href={href} noLinkLayout forceExternal>
+                    {/* eslint-disable-next-line @next/next/no-img-element */}
+                    <img className={classes.image} src={src} alt={alt} width={650} height="auto" />
+                </Link>
+            ) : (
+                /* eslint-disable-next-line @next/next/no-img-element */
                 <img className={classes.image} src={src} alt={alt} width={650} height="auto" />
-            </Link>
+            )}
+
             {title && (
                 <figcaption className="gatsby-resp-image-figcaption">
                     <MarkdownToReact markdown={title} />
@@ -104,7 +110,7 @@ const Image = ({ src, alt, title, href, ...props }) => {
 const ImageFill = ({ image, ...props }) => {
     return (
         <span
-            class={classes['figure-fill']}
+            className={classes['figure-fill']}
             style={{ paddingBottom: `${(image.height / image.width) * 100}%` }}
         >
             <ImageNext src={image.src} {...props} fill />

website/src/components/footer.js

@@ -21,7 +21,7 @@ export default function Footer({ wide = false }) {
                             <li className={classes.label}>{label}</li>
                             {items.map(({ text, url }, j) => (
                                 <li key={j}>
-                                    <Link to={url} hidden>
+                                    <Link to={url} noLinkLayout>
                                         {text}
                                     </Link>
                                 </li>
@@ -42,14 +42,14 @@ export default function Footer({ wide = false }) {
             <div className={classNames(classes.content, classes.copy)}>
                 <span>
                     &copy; 2016-{new Date().getFullYear()}{' '}
-                    <Link to={companyUrl} hidden>
+                    <Link to={companyUrl} noLinkLayout>
                         {company}
                     </Link>
                 </span>
-                <Link to={companyUrl} aria-label={company} hidden className={classes.logo}>
+                <Link to={companyUrl} aria-label={company} noLinkLayout className={classes.logo}>
                     <SVG src={explosionLogo.src} width={45} height={45} />
                 </Link>
-                <Link to={`${companyUrl}/legal`} hidden>
+                <Link to={`${companyUrl}/legal`} noLinkLayout>
                     Legal / Imprint
                 </Link>
             </div>

website/src/components/github.js

@@ -5,7 +5,7 @@ import classNames from 'classnames'
 import Icon from './icon'
 import Link from './link'
 import classes from '../styles/code.module.sass'
-import { Code } from './code'
+import Code from './codeDynamic'
 
 const defaultErrorMsg = `Can't fetch code example from GitHub :(
 
@@ -42,7 +42,7 @@ const GitHubCode = ({ url, lang, errorMsg = defaultErrorMsg, className }) => {
     return (
         <>
             <header className={classes.header}>
-                <Link to={url} hidden>
+                <Link to={url} noLinkLayout>
                     <Icon name="github" width={16} inline />
                     <code
                         className={classNames(classes['inline-code'], classes['inline-code-dark'])}

website/src/components/htmlToReact.js

@@ -0,0 +1,12 @@
+import { Parser as HtmlToReactParser } from 'html-to-react'
+
+const htmlToReactParser = new HtmlToReactParser()
+/**
+ * Convert raw HTML to React elements
+ * @param {string} html - The HTML markup to convert.
+ * @returns {Node} - The converted React elements.
+ */
+
+export default function HtmlToReact(props) {
+    return htmlToReactParser.parse(props.children)
+}

website/src/components/inlineCode.js

@@ -0,0 +1,23 @@
+import React from 'react'
+import PropTypes from 'prop-types'
+import classNames from 'classnames'
+import { isString } from './util'
+import classes from '../styles/code.module.sass'
+
+const WRAP_THRESHOLD = 30
+
+export const InlineCode = ({ wrap = false, className, children, ...props }) => {
+    const codeClassNames = classNames(classes['inline-code'], className, {
+        [classes['wrap']]: wrap || (isString(children) && children.length >= WRAP_THRESHOLD),
+    })
+    return (
+        <code className={codeClassNames} {...props}>
+            {children}
+        </code>
+    )
+}
+InlineCode.propTypes = {
+    wrap: PropTypes.bool,
+    className: PropTypes.string,
+    children: PropTypes.node,
+}

website/src/components/juniper.js

@@ -12,17 +12,17 @@ const spacyTheme = createTheme({
     theme: 'dark',
     settings: {
         background: 'var(--color-front)',
-        foreground: 'var(--color-subtle)',
+        foreground: 'var(--color-subtle-on-dark)',
         caret: 'var(--color-theme-dark)',
-        selection: 'var(--color-theme)',
+        selection: 'var(--color-theme-dark)',
-        selectionMatch: 'var(--color-theme)',
+        selectionMatch: 'var(--color-theme-dark)',
         gutterBackground: 'var(--color-front)',
-        gutterForeground: 'var(--color-subtle)',
+        gutterForeground: 'var(--color-subtle-on-dark)',
         fontFamily: 'var(--font-code)',
     },
     styles: [
         { tag: t.comment, color: 'var(--syntax-comment)' },
-        { tag: t.variableName, color: 'var(--color-subtle)' },
+        { tag: t.variableName, color: 'var(--color-subtle-on-dark)' },
         { tag: [t.string, t.special(t.brace)], color: '#fff' },
         { tag: t.number, color: 'var(--syntax-number)' },
         { tag: t.string, color: 'var(--syntax-selector)' },

website/src/components/landing.js

@@ -1,17 +1,17 @@
 import React from 'react'
 import classNames from 'classnames'
 
-import patternDefault from '../images/pattern_blue.jpg'
+import patternDefault from '../images/pattern_blue.png'
-import patternNightly from '../images/pattern_nightly.jpg'
+import patternNightly from '../images/pattern_nightly.png'
-import patternLegacy from '../images/pattern_legacy.jpg'
+import patternLegacy from '../images/pattern_legacy.png'
-import overlayDefault from '../images/pattern_landing.jpg'
+import overlayDefault from '../images/pattern_landing.png'
-import overlayNightly from '../images/pattern_landing_nightly.jpg'
+import overlayNightly from '../images/pattern_landing_nightly.png'
-import overlayLegacy from '../images/pattern_landing_legacy.jpg'
+import overlayLegacy from '../images/pattern_landing_legacy.png'
 
 import Grid from './grid'
 import { Content } from './main'
 import Button from './button'
-import CodeBlock from './code'
+import CodeBlock from './codeBlock'
 import { H1, H2, H3 } from './typography'
 import Link from './link'
 import classes from '../styles/landing.module.sass'
@@ -110,6 +110,7 @@ export const LandingBanner = ({
     })
     const style = {
         '--color-theme': background,
+        '--color-theme-dark': background,
         '--color-back': color,
         backgroundImage: backgroundImage ? `url(${backgroundImage})` : null,
     }
@@ -124,7 +125,7 @@ export const LandingBanner = ({
                                 <span className={classes['label']}>{label}</span>
                             </div>
                         )}
-                        <Link to={to} hidden>
+                        <Link to={to} noLinkLayout>
                             {title}
                         </Link>
                     </Heading>

website/src/components/link.js

@@ -26,7 +26,7 @@ export default function Link({
     to,
     href,
     onClick,
-    hidden = false,
+    noLinkLayout = false,
     hideIcon = false,
     ws = false,
     forceExternal = false,
@@ -36,10 +36,10 @@ export default function Link({
     const dest = to || href
     const external = forceExternal || /(http(s?)):\/\//gi.test(dest)
     const icon = getIcon(dest)
-    const withIcon = !hidden && !hideIcon && !!icon && !isImage(children)
+    const withIcon = !noLinkLayout && !hideIcon && !!icon && !isImage(children)
     const sourceWithText = withIcon && isString(children)
     const linkClassNames = classNames(classes.root, className, {
-        [classes.hidden]: hidden,
+        [classes['no-link-layout']]: noLinkLayout,
         [classes.nowrap]: (withIcon && !sourceWithText) || icon === 'network',
         [classes['with-icon']]: withIcon,
     })
@@ -97,7 +97,7 @@ Link.propTypes = {
     to: PropTypes.string,
     href: PropTypes.string,
     onClick: PropTypes.func,
-    hidden: PropTypes.bool,
+    noLinkLayout: PropTypes.bool,
     hideIcon: PropTypes.bool,
     ws: PropTypes.bool,
     className: PropTypes.string,

website/src/components/main.js

@@ -2,11 +2,11 @@ import React from 'react'
 import PropTypes from 'prop-types'
 import classNames from 'classnames'
 
-import patternBlue from '../images/pattern_blue.jpg'
+import patternBlue from '../images/pattern_blue.png'
-import patternGreen from '../images/pattern_green.jpg'
+import patternGreen from '../images/pattern_green.png'
-import patternPurple from '../images/pattern_purple.jpg'
+import patternPurple from '../images/pattern_purple.png'
-import patternNightly from '../images/pattern_nightly.jpg'
+import patternNightly from '../images/pattern_nightly.png'
-import patternLegacy from '../images/pattern_legacy.jpg'
+import patternLegacy from '../images/pattern_legacy.png'
 import classes from '../styles/main.module.sass'
 
 const patterns = {

website/src/components/markdownToReact.js

@@ -0,0 +1,32 @@
+import React, { useEffect, useState } from 'react'
+import { serialize } from 'next-mdx-remote/serialize'
+import { MDXRemote } from 'next-mdx-remote'
+import remarkPlugins from '../../plugins/index.mjs'
+
+/**
+ * Convert raw Markdown to React
+ * @param {String} markdown - The Markdown markup to convert.
+ * @param {Object} [remarkReactComponents] - Optional React components to use
+ *  for HTML elements.
+ * @returns {Node} - The converted React elements.
+ */
+export default function MarkdownToReact({ markdown }) {
+    const [mdx, setMdx] = useState(null)
+
+    useEffect(() => {
+        const getMdx = async () => {
+            setMdx(
+                await serialize(markdown, {
+                    parseFrontmatter: false,
+                    mdxOptions: {
+                        remarkPlugins,
+                    },
+                })
+            )
+        }
+
+        getMdx()
+    }, [markdown])
+
+    return mdx ? <MDXRemote {...mdx} /> : <></>
+}

website/src/components/markdownToReactDynamic.js

@@ -0,0 +1,5 @@
+import dynamic from 'next/dynamic'
+
+export default dynamic(() => import('./markdownToReact'), {
+    loading: () => <p>Loading...</p>,
+})

website/src/components/navigation.js

@@ -30,7 +30,7 @@ const NavigationDropdown = ({ items = [], section }) => {
 
 export default function Navigation({ title, items = [], section, search, alert, children }) {
     const logo = (
-        <Link to="/" aria-label={title} hidden>
+        <Link to="/" aria-label={title} noLinkLayout>
             <h1 className={classes.title}>{title}</h1>
             <SVG src={logoSpacy.src} className={classes.logo} width={300} height={96} />
         </Link>
@@ -57,7 +57,7 @@ export default function Navigation({ title, items = [], section, search, alert,
                         })
                         return (
                             <li key={i} className={itemClassNames}>
-                                <Link to={url} tabIndex={isActive ? '-1' : null} hidden>
+                                <Link to={url} tabIndex={isActive ? '-1' : null} noLinkLayout>
                                     {text}
                                 </Link>
                             </li>

website/src/components/quickstart.js

@@ -251,7 +251,12 @@ const Quickstart = ({
                     </menu>
                 </pre>
                 {showCopy && (
-                    <textarea ref={copyAreaRef} className={classes['copy-area']} rows={1} />
+                    <textarea
+                        ref={copyAreaRef}
+                        className={classes['copy-area']}
+                        rows={1}
+                        aria-label={`Interactive code example for ${title}`}
+                    />
                 )}
             </div>
         </Container>

website/src/components/readnext.js

@@ -9,15 +9,15 @@ import classes from '../styles/readnext.module.sass'
 
 export default function ReadNext({ title, to }) {
     return (
-        <div className={classes.root}>
+        <Link to={to} noLinkLayout className={classes.root}>
-            <Link to={to} hidden>
+            <span>
                 <Label>Read next</Label>
                 {title}
-            </Link>
+            </span>
-            <Link to={to} hidden className={classes.icon} aria-hidden="true">
+            <span className={classes.icon}>
-                <Icon name="arrowright" />
+                <Icon name="arrowright" aria-hidden="true" />
-            </Link>
+            </span>
-        </div>
+        </Link>
     )
 }
 

website/src/components/seo.js

@@ -9,6 +9,8 @@ import socialImageLegacy from '../images/social_legacy.jpg'
 import siteMetadata from '../../meta/site.json'
 import Head from 'next/head'
 
+import { siteUrl } from '../../meta/dynamicMeta.mjs'
+
 function getPageTitle(title, sitename, slogan, sectionTitle, nightly, legacy) {
     if (sectionTitle && title) {
         const suffix = nightly ? ' (nightly)' : legacy ? ' (legacy)' : ''
@@ -25,7 +27,7 @@ function getImage(section, nightly, legacy) {
     if (legacy) return socialImageLegacy
     if (section === 'api') return socialImageApi
     if (section === 'universe') return socialImageUniverse
-    return socialImageDefault
+    return `${siteUrl}${socialImageDefault.src}`
 }
 
 export default function SEO({
@@ -46,7 +48,7 @@ export default function SEO({
         nightly,
         legacy
     )
-    const socialImage = getImage(section, nightly, legacy).src
+    const socialImage = getImage(section, nightly, legacy)
     const meta = [
         {
             name: 'description',

website/src/components/title.js

@@ -5,7 +5,7 @@ import classNames from 'classnames'
 import Button from './button'
 import Tag from './tag'
 import { OptionalLink } from './link'
-import { InlineCode } from './code'
+import { InlineCode } from './inlineCode'
 import { H1, Label, InlineList, Help } from './typography'
 import Icon from './icon'
 
@@ -51,8 +51,7 @@ export default function Title({
 
                     {image && (
                         <div className={classes.image}>
-                            {/* eslint-disable-next-line @next/next/no-img-element */}
+                            <Image src={image} width={100} height={100} alt={`${title} Logo`} />
-                            <img src={image} width={100} height={100} alt="" />
                         </div>
                     )}
                 </div>

website/src/components/typeAnnotation.js

@@ -0,0 +1,51 @@
+import React from 'react'
+import classNames from 'classnames'
+import CUSTOM_TYPES from '../../meta/type-annotations.json'
+import Link from './link'
+import classes from '../styles/code.module.sass'
+
+export const WRAP_THRESHOLD = 30
+
+const specialCharacterList = ['[', ']', ',', ', ']
+
+const highlight = (element) =>
+    specialCharacterList.includes(element) ? (
+        <span className={classes['cli-arg-subtle']}>{element}</span>
+    ) : (
+        element
+    )
+
+function linkType(el, showLink = true, key) {
+    if (!el.length) return el
+    const elStr = el.trim()
+    if (!elStr) return el
+    const typeUrl = CUSTOM_TYPES[elStr]
+    const url = typeUrl == true ? DEFAULT_TYPE_URL : typeUrl
+    return url && showLink ? (
+        <Link to={url} hideIcon key={key}>
+            {elStr}
+        </Link>
+    ) : (
+        highlight(el)
+    )
+}
+
+export const TypeAnnotation = ({ lang = 'python', link = true, children }) => {
+    const code = Array.isArray(children) ? children.join('') : children || ''
+    const [rawText, meta] = code.split(/(?= \(.+\)$)/)
+    const annotClassNames = classNames(
+        'type-annotation',
+        `language-${lang}`,
+        classes['inline-code'],
+        classes['type-annotation'],
+        {
+            [classes['wrap']]: code.length >= WRAP_THRESHOLD,
+        }
+    )
+    return (
+        <span className={annotClassNames} role="code" aria-label="Type annotation">
+            {rawText.split(/(\[|\]|,)/).map((el, i) => linkType(el, !!link, i))}
+            {meta && <span className={classes['type-annotation-meta']}>{meta}</span>}
+        </span>
+    )
+}

website/src/components/util.js

@@ -1,12 +1,6 @@
-import React, { Fragment, useEffect, useState } from 'react'
+import React, { Fragment } from 'react'
-import { Parser as HtmlToReactParser } from 'html-to-react'
 import siteMetadata from '../../meta/site.json'
 import { domain } from '../../meta/dynamicMeta.mjs'
-import remarkPlugins from '../../plugins/index.mjs'
-import { serialize } from 'next-mdx-remote/serialize'
-import { MDXRemote } from 'next-mdx-remote'
-
-const htmlToReactParser = new HtmlToReactParser()
 
 const isNightly = siteMetadata.nightlyBranches.includes(domain)
 export const DEFAULT_BRANCH = isNightly ? 'develop' : 'master'
@@ -70,43 +64,6 @@ export function isEmptyObj(obj) {
     return Object.entries(obj).length === 0 && obj.constructor === Object
 }
 
-/**
- * Convert raw HTML to React elements
- * @param {string} html - The HTML markup to convert.
- * @returns {Node} - The converted React elements.
- */
-export function htmlToReact(html) {
-    return htmlToReactParser.parse(html)
-}
-
-/**
- * Convert raw Markdown to React
- * @param {String} markdown - The Markdown markup to convert.
- * @param {Object} [remarkReactComponents] - Optional React components to use
- *  for HTML elements.
- * @returns {Node} - The converted React elements.
- */
-export function MarkdownToReact({ markdown }) {
-    const [mdx, setMdx] = useState(null)
-
-    useEffect(() => {
-        const getMdx = async () => {
-            setMdx(
-                await serialize(markdown, {
-                    parseFrontmatter: false,
-                    mdxOptions: {
-                        remarkPlugins,
-                    },
-                })
-            )
-        }
-
-        getMdx()
-    }, [markdown])
-
-    return mdx ? <MDXRemote {...mdx} /> : <></>
-}
-
 /**
  * Join an array of nodes with a given string delimiter, like Array.join for React
  * @param {Array} arr - The elements to join.

website/src/images/explosion.svg

@@ -1,3 +1,3 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 500 500" width="200" height="200">
+<svg height="100" viewBox="0 0 100 100" width="100" xmlns="http://www.w3.org/2000/svg">
-    <path fill="currentColor" d="M111.7 74.9L91.2 93.1l9.1 10.2 17.8-15.8 7.4 8.4-17.8 15.8 10.1 11.4 20.6-18.2 7.7 8.7-30.4 26.9-41.9-47.3 30.3-26.9 7.6 8.6zM190.8 59.6L219 84.3l-14.4 4.5-20.4-18.2-6.4 26.6-14.4 4.5 8.9-36.4-26.9-24.1 14.3-4.5L179 54.2l5.7-25.2 14.3-4.5-8.2 35.1zM250.1 21.2l27.1 3.4c6.1.8 10.8 3.1 14 7.2 3.2 4.1 4.5 9.2 3.7 15.5-.8 6.3-3.2 11-7.4 14.1-4.1 3.1-9.2 4.3-15.3 3.5L258 63.2l-2.8 22.3-13-1.6 7.9-62.7zm11.5 13l-2.2 17.5 12.6 1.6c5.1.6 9.1-2 9.8-7.6.7-5.6-2.5-9.2-7.6-9.9l-12.6-1.6zM329.1 95.4l23.8 13.8-5.8 10L312 98.8l31.8-54.6 11.3 6.6-26 44.6zM440.5 145c-1.3 8.4-5.9 15.4-13.9 21.1s-16.2 7.7-24.6 6.1c-8.4-1.6-15.3-6.3-20.8-14.1-5.5-7.9-7.6-16-6.4-24.4 1.3-8.5 6-15.5 14-21.1 8-5.6 16.2-7.7 24.5-6 8.4 1.6 15.4 6.3 20.9 14.2 5.5 7.6 7.6 15.7 6.3 24.2zM412 119c-5.1-.8-10.3.6-15.6 4.4-5.2 3.7-8.4 8.1-9.4 13.2-1 5.2.2 10.1 3.5 14.8 3.4 4.8 7.5 7.5 12.7 8.2 5.2.8 10.4-.7 15.6-4.4 5.3-3.7 8.4-8.1 9.4-13.2 1.1-5.1-.1-9.9-3.4-14.7-3.4-4.8-7.6-7.6-12.8-8.3zM471.5 237.9c-2.8 4.8-7.1 7.6-13 8.7l-2.6-13.1c5.3-.9 8.1-5 7.2-11-.9-5.8-4.3-8.8-8.9-8.2-2.3.3-3.7 1.4-4.5 3.3-.7 1.9-1.4 5.2-1.7 10.1-.8 7.5-2.2 13.1-4.3 16.9-2.1 3.9-5.7 6.2-10.9 7-6.3.9-11.3-.5-15.2-4.4-3.9-3.8-6.3-9-7.3-15.7-1.1-7.4-.2-13.7 2.6-18.8 2.8-5.1 7.4-8.2 13.7-9.2l2.6 13c-5.6 1.1-8.7 6.6-7.7 13.4 1 6.6 3.9 9.5 8.6 8.8 4.4-.7 5.7-4.5 6.7-14.1.3-3.5.7-6.2 1.1-8.4.4-2.2 1.2-4.4 2.2-6.8 2.1-4.7 6-7.2 11.8-8.1 5.4-.8 10.3.4 14.5 3.7 4.2 3.3 6.9 8.5 8 15.6.9 6.9-.1 12.6-2.9 17.3zM408.6 293.5l2.4-12.9 62 11.7-2.4 12.9-62-11.7zM419.6 396.9c-8.3 2-16.5.3-24.8-5-8.2-5.3-13.2-12.1-14.9-20.5-1.6-8.4.1-16.6 5.3-24.6 5.2-8.1 11.9-13.1 20.2-15.1 8.4-1.9 16.6-.3 24.9 5 8.2 5.3 13.2 12.1 14.8 20.5 1.7 8.4 0 16.6-5.2 24.7-5.2 8-12 13-20.3 15zm13.4-36.3c-1.2-5.1-4.5-9.3-9.9-12.8s-10.6-4.7-15.8-3.7-9.3 4-12.4 8.9-4.1 9.8-2.8 14.8c1.2 5.1 4.5 9.3 9.9 12.8 5.5 3.5 10.7 4.8 15.8 3.7 5.1-.9 9.2-3.8 12.3-8.7s4.1-9.9 2.9-15zM303.6 416.5l9.6-5.4 43.3 20.4-19.2-34 11.4-6.4 31 55-9.6 5.4-43.4-20.5 19.2 34.1-11.3 6.4-31-55zM238.2 468.8c-49 0-96.9-17.4-134.8-49-38.3-32-64-76.7-72.5-125.9-2-11.9-3.1-24-3.1-35.9 0-36.5 9.6-72.6 27.9-104.4 2.1-3.6 6.7-4.9 10.3-2.8 3.6 2.1 4.9 6.7 2.8 10.3-16.9 29.5-25.9 63.1-25.9 96.9 0 11.1 1 22.3 2.9 33.4 7.9 45.7 31.8 87.2 67.3 116.9 35.2 29.3 79.6 45.5 125.1 45.5 11.1 0 22.3-1 33.4-2.9 4.1-.7 8 2 8.7 6.1.7 4.1-2 8-6.1 8.7-11.9 2-24 3.1-36 3.1z" />
+    <path d="M22.8 11.9l1.5 1.7-4.4 3.8 1.8 2 4-3.5 1.4 1.6-4 3.5 1.9 2.2 4.4-3.8 1.5 1.7-6.3 5.5-8-9.3 6.2-5.4zm17.1-1.2l5.9 4.8-2.8.8-4-3.3-1.5 4.9-2.7.8 2.3-7.2-5.6-4.6 2.8-.8 3.7 3 1.5-4.6 2.7-.8-2.3 7zm14.1.9l-.6 4.2-2.5-.4 1.8-12.1 4.9.7c2.6.4 4.1 2 3.7 4.6s-2.3 3.7-4.9 3.3l-2.4-.3zm3.2-5.4l-2.3-.3-.5 3.6 2.3.3c1.3.2 2.1-.5 2.2-1.5.1-1.1-.4-1.9-1.7-2.1zm14.5 2.4l2.2 1.4-5.4 8.4 4.8 3.1-1.2 1.9-7-4.5 6.6-10.3zm6.8 22.8c-1.9-2.9-.9-6.3 2.1-8.3 3.1-2 6.6-1.5 8.5 1.4s1 6.3-2.1 8.3c-3 2-6.6 1.4-8.5-1.4zm8.7-5.7c-1.1-1.6-3.1-1.8-5.1-.5s-2.7 3.3-1.6 4.9 3.2 1.8 5.2.5c1.9-1.3 2.6-3.3 1.5-4.9zm-.1 17c-1 .5-1.4 1.4-1.2 2.6s.8 2 1.8 1.8c.7-.1 1.1-.6 1.2-1.7l.2-2.2c.2-1.8.9-3.3 2.9-3.5 2.2-.3 4 1.3 4.3 3.9.4 2.8-.9 4.6-2.9 5.2l-.3-2.5c.8-.4 1.3-1.2 1.2-2.4-.2-1.1-.8-1.8-1.7-1.7-.7.1-1 .6-1.1 1.5l-.3 2.3c-.2 2-1.2 3.4-3 3.6-2.4.3-4-1.4-4.4-4-.4-2.7.7-4.8 3-5.5l.3 2.6zm-3.8 15.6l.5-2.5 12 2.5-.5 2.5-12-2.5zm-4.7 10.3c1.9-2.9 5.4-3.4 8.5-1.4s4 5.5 2.1 8.3-5.4 3.4-8.5 1.4-4-5.5-2.1-8.3zm8.7 5.6c1.1-1.6.4-3.6-1.7-4.9-2-1.3-4.1-1.2-5.1.5-1.1 1.6-.4 3.6 1.6 4.9 2 1.4 4.1 1.2 5.2-.5zm-24.7 8.1l1.8-1 9.1 4.2-4.1-7.1 2.1-1.2 6.1 10.6-2 1.2-8.6-4 3.9 6.7-2.1 1.2-6.2-10.6zM50 92.2C26.7 92.2 7.8 73.3 7.8 50c0-7.2 1.8-14.3 5.3-20.5.4-.7 1.3-1 2-.6s1 1.3.6 2a39.53 39.53 0 0 0-4.9 19c0 21.6 17.6 39.2 39.2 39.2 2.2 0 4.4-.2 6.6-.5.8-.1 1.6.4 1.7 1.2s-.4 1.6-1.2 1.7c-2.4.5-4.7.7-7.1.7z"/>
-</svg>
+</svg>