Merge branch 'develop' of https://github.com/explosion/spaCy into develop

bin/ud/ud_train.py

@@ -78,8 +78,7 @@ def read_data(
                 head = int(head) - 1 if head != "0" else id_
                 sent["words"].append(word)
                 sent["tags"].append(tag)
-                sent["morphology"].append(_parse_morph_string(morph))
+                sent["morphs"].append(_compile_morph_string(morph, pos))
-                sent["morphology"][-1].add("POS_%s" % pos)
                 sent["heads"].append(head)
                 sent["deps"].append("ROOT" if dep == "root" else dep)
                 sent["spaces"].append(space_after == "_")
@@ -88,12 +87,12 @@ def read_data(
             if oracle_segments:
                 docs.append(Doc(nlp.vocab, words=sent["words"], spaces=sent["spaces"]))
                 golds.append(sent)
-                assert golds[-1].morphology is not None
+                assert golds[-1]["morphs"] is not None
 
             sent_annots.append(sent)
             if raw_text and max_doc_length and len(sent_annots) >= max_doc_length:
                 doc, gold = _make_gold(nlp, None, sent_annots)
-                assert gold.morphology is not None
+                assert gold["morphs"] is not None
                 sent_annots = []
                 docs.append(doc)
                 golds.append(gold)
@@ -109,17 +108,10 @@ def read_data(
     return golds_to_gold_data(docs, golds)
 
 
-def _parse_morph_string(morph_string):
+def _compile_morph_string(morph_string, pos):
     if morph_string == '_':
-        return set()
+        return f"POS={pos}"
-    output = []
+    return morph_string + f"|POS={pos}"
-    replacements = {'1': 'one', '2': 'two', '3': 'three'}
-    for feature in morph_string.split('|'):
-        key, value = feature.split('=')
-        value = replacements.get(value, value)
-        value = value.split(',')[0]
-        output.append('%s_%s' % (key, value.lower()))
-    return set(output)
 
 
 def read_conllu(file_):
@@ -155,7 +147,7 @@ def _make_gold(nlp, text, sent_annots, drop_deps=0.0):
     sent_starts = []
     for sent in sent_annots:
         gold["heads"].extend(len(gold["words"])+head for head in sent["heads"])
-        for field in ["words", "tags", "deps", "morphology", "entities", "spaces"]:
+        for field in ["words", "tags", "deps", "morphs", "entities", "spaces"]:
             gold[field].extend(sent[field])
         sent_starts.append(True)
         sent_starts.extend([False] * (len(sent["words"]) - 1))
@@ -168,7 +160,7 @@ def _make_gold(nlp, text, sent_annots, drop_deps=0.0):
     doc = nlp.make_doc(text)
     gold.pop("spaces")
     gold["sent_starts"] = sent_starts
-    for i in range(len(gold.heads)):
+    for i in range(len(gold["heads"])):
         if random.random() < drop_deps:
             gold["heads"][i] = None
             gold["labels"][i] = None
@@ -185,7 +177,7 @@ def golds_to_gold_data(docs, golds):
     """Get out the training data format used by begin_training"""
     data = []
     for doc, gold in zip(docs, golds):
-        example = Example.from_dict(doc, gold)
+        example = Example.from_dict(doc, dict(gold))
         data.append(example)
     return data
 
@@ -354,8 +346,7 @@ def initialize_pipeline(nlp, examples, config, device):
     if config.multitask_sent:
         nlp.parser.add_multitask_objective("sent_start")
     for eg in examples:
-        gold = eg.gold
+        for tag in eg.get_aligned("TAG", as_string=True):
-        for tag in gold.tags:
             if tag is not None:
                 nlp.tagger.add_label(tag)
     if torch is not None and device != -1:
@@ -489,10 +480,6 @@ def main(
     Token.set_extension("begins_fused", default=False)
     Token.set_extension("inside_fused", default=False)
 
-    Token.set_extension("get_conllu_lines", method=get_token_conllu)
-    Token.set_extension("begins_fused", default=False)
-    Token.set_extension("inside_fused", default=False)
-
     spacy.util.fix_random_seed()
     lang.zh.Chinese.Defaults.use_jieba = False
     lang.ja.Japanese.Defaults.use_janome = False
@@ -535,10 +522,10 @@ def main(
         else:
             batches = minibatch(examples, size=batch_sizes)
         losses = {}
-        n_train_words = sum(len(eg.doc) for eg in examples)
+        n_train_words = sum(len(eg.predicted) for eg in examples)
         with tqdm.tqdm(total=n_train_words, leave=False) as pbar:
             for batch in batches:
-                pbar.update(sum(len(ex.doc) for ex in batch))
+                pbar.update(sum(len(ex.predicted) for ex in batch))
                 nlp.parser.cfg["beam_update_prob"] = next(beam_prob)
                 nlp.update(
                     batch,

examples/training/conllu.py

@@ -283,7 +283,7 @@ def initialize_pipeline(nlp, examples, config):
     nlp.parser.moves.add_action(2, "subtok")
     nlp.add_pipe(nlp.create_pipe("tagger"))
     for eg in examples:
-        for tag in eg.gold.tags:
+        for tag in eg.get_aligned("TAG", as_string=True):
             if tag is not None:
                 nlp.tagger.add_label(tag)
     # Replace labels that didn't make the frequency cutoff

examples/training/train_ner.py

@@ -56,7 +56,7 @@ def main(model=None, output_dir=None, n_iter=100):
             print("Add label", ent[2])
             ner.add_label(ent[2])
 
-    with nlp.select_pipes(enable="ner") and warnings.catch_warnings():
+    with nlp.select_pipes(enable="simple_ner") and warnings.catch_warnings():
         # show warnings for misaligned entity spans once
         warnings.filterwarnings("once", category=UserWarning, module="spacy")
 

pyproject.toml

@@ -6,7 +6,7 @@ requires = [
     "cymem>=2.0.2,<2.1.0",
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
-    "thinc==8.0.0a9",
+    "thinc==8.0.0a11",
     "blis>=0.4.0,<0.5.0"
 ]
 build-backend = "setuptools.build_meta"

spacy/about.py

@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.0.0.dev10"
+__version__ = "3.0.0.dev12"
 __release__ = True
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"

spacy/cli/__init__.py

@@ -15,6 +15,8 @@ from .evaluate import evaluate  # noqa: F401
 from .convert import convert  # noqa: F401
 from .init_model import init_model  # noqa: F401
 from .validate import validate  # noqa: F401
+from .project import project_clone, project_assets, project_run  # noqa: F401
+from .project import project_run_all  # noqa: F401
 
 
 @app.command("link", no_args_is_help=True, deprecated=True, hidden=True)

spacy/cli/_app.py

@@ -1,4 +1,3 @@
-from typing import Optional
 import typer
 from typer.main import get_command
 

spacy/cli/debug_data.py

@@ -102,9 +102,6 @@ def debug_data(
         corpus = Corpus(train_path, dev_path)
         try:
             train_dataset = list(corpus.train_dataset(nlp))
-            train_dataset_unpreprocessed = list(
-                corpus.train_dataset_without_preprocessing(nlp)
-            )
         except ValueError as e:
             loading_train_error_message = f"Training data cannot be loaded: {e}"
         try:
@@ -120,11 +117,9 @@ def debug_data(
     msg.good("Corpus is loadable")
 
     # Create all gold data here to avoid iterating over the train_dataset constantly
-    gold_train_data = _compile_gold(train_dataset, pipeline, nlp)
+    gold_train_data = _compile_gold(train_dataset, pipeline, nlp, make_proj=True)
-    gold_train_unpreprocessed_data = _compile_gold(
+    gold_train_unpreprocessed_data = _compile_gold(train_dataset, pipeline, nlp, make_proj=False)
-        train_dataset_unpreprocessed, pipeline
+    gold_dev_data = _compile_gold(dev_dataset, pipeline, nlp, make_proj=True)
-    )
-    gold_dev_data = _compile_gold(dev_dataset, pipeline, nlp)
 
     train_texts = gold_train_data["texts"]
     dev_texts = gold_dev_data["texts"]
@@ -497,7 +492,7 @@ def _load_file(file_path: Path, msg: Printer) -> None:
 
 
 def _compile_gold(
-    examples: Sequence[Example], pipeline: List[str], nlp: Language
+    examples: Sequence[Example], pipeline: List[str], nlp: Language, make_proj: bool
 ) -> Dict[str, Any]:
     data = {
         "ner": Counter(),
@@ -517,9 +512,9 @@ def _compile_gold(
         "n_cats_multilabel": 0,
         "texts": set(),
     }
-    for example in examples:
+    for eg in examples:
-        gold = example.reference
+        gold = eg.reference
-        doc = example.predicted
+        doc = eg.predicted
         valid_words = [x for x in gold if x is not None]
         data["words"].update(valid_words)
         data["n_words"] += len(valid_words)
@@ -530,7 +525,7 @@ def _compile_gold(
                 if nlp.vocab.strings[word] not in nlp.vocab.vectors:
                     data["words_missing_vectors"].update([word])
         if "ner" in pipeline:
-            for i, label in enumerate(gold.ner):
+            for i, label in enumerate(eg.get_aligned_ner()):
                 if label is None:
                     continue
                 if label.startswith(("B-", "U-", "L-")) and doc[i].is_space:
@@ -556,16 +551,18 @@ def _compile_gold(
             if list(gold.cats.values()).count(1.0) != 1:
                 data["n_cats_multilabel"] += 1
         if "tagger" in pipeline:
-            data["tags"].update([x for x in gold.tags if x is not None])
+            tags = eg.get_aligned("TAG", as_string=True)
+            data["tags"].update([x for x in tags if x is not None])
         if "parser" in pipeline:
-            data["deps"].update([x for x in gold.labels if x is not None])
+            aligned_heads, aligned_deps = eg.get_aligned_parse(projectivize=make_proj)
-            for i, (dep, head) in enumerate(zip(gold.labels, gold.heads)):
+            data["deps"].update([x for x in aligned_deps if x is not None])
+            for i, (dep, head) in enumerate(zip(aligned_deps, aligned_heads)):
                 if head == i:
                     data["roots"].update([dep])
                     data["n_sents"] += 1
-            if nonproj.is_nonproj_tree(gold.heads):
+            if nonproj.is_nonproj_tree(aligned_heads):
                 data["n_nonproj"] += 1
-            if nonproj.contains_cycle(gold.heads):
+            if nonproj.contains_cycle(aligned_heads):
                 data["n_cycles"] += 1
     return data
 
@@ -581,7 +578,7 @@ def _get_examples_without_label(data: Sequence[Example], label: str) -> int:
     for eg in data:
         labels = [
             label.split("-")[1]
-            for label in eg.gold.ner
+            for label in eg.get_aligned_ner()
             if label not in ("O", "-", None)
         ]
         if label not in labels:

spacy/cli/evaluate.py

@@ -1,7 +1,9 @@
-from typing import Optional, List
+from typing import Optional, List, Dict
 from timeit import default_timer as timer
 from wasabi import Printer
 from pathlib import Path
+import re
+import srsly
 
 from ..gold import Corpus
 from ..tokens import Doc
@@ -16,13 +18,12 @@ def evaluate_cli(
     # fmt: off
     model: str = Arg(..., help="Model name or path"),
     data_path: Path = Arg(..., help="Location of JSON-formatted evaluation data", exists=True),
+    output: Optional[Path] = Opt(None, "--output", "-o", help="Output JSON file for metrics", dir_okay=False),
     gpu_id: int = Opt(-1, "--gpu-id", "-g", help="Use GPU"),
     gold_preproc: bool = Opt(False, "--gold-preproc", "-G", help="Use gold preprocessing"),
     displacy_path: Optional[Path] = Opt(None, "--displacy-path", "-dp", help="Directory to output rendered parses as HTML", exists=True, file_okay=False),
     displacy_limit: int = Opt(25, "--displacy-limit", "-dl", help="Limit of parses to render as HTML"),
-    return_scores: bool = Opt(False, "--return-scores", "-R", help="Return dict containing model scores"),
+    # fmt: on
-
-        # fmt: on
 ):
     """
     Evaluate a model. To render a sample of parses in a HTML file, set an
@@ -31,24 +32,24 @@ def evaluate_cli(
     evaluate(
         model,
         data_path,
+        output=output,
         gpu_id=gpu_id,
         gold_preproc=gold_preproc,
         displacy_path=displacy_path,
         displacy_limit=displacy_limit,
         silent=False,
-        return_scores=return_scores,
     )
 
 
 def evaluate(
     model: str,
     data_path: Path,
+    output: Optional[Path],
     gpu_id: int = -1,
     gold_preproc: bool = False,
     displacy_path: Optional[Path] = None,
     displacy_limit: int = 25,
     silent: bool = True,
-    return_scores: bool = False,
 ) -> Scorer:
     msg = Printer(no_print=silent, pretty=not silent)
     util.fix_random_seed()
@@ -56,21 +57,19 @@ def evaluate(
         util.use_gpu(gpu_id)
     util.set_env_log(False)
     data_path = util.ensure_path(data_path)
+    output_path = util.ensure_path(output)
     displacy_path = util.ensure_path(displacy_path)
     if not data_path.exists():
         msg.fail("Evaluation data not found", data_path, exits=1)
     if displacy_path and not displacy_path.exists():
         msg.fail("Visualization output directory not found", displacy_path, exits=1)
     corpus = Corpus(data_path, data_path)
-    if model.startswith("blank:"):
+    nlp = util.load_model(model)
-        nlp = util.get_lang_class(model.replace("blank:", ""))()
-    else:
-        nlp = util.load_model(model)
     dev_dataset = list(corpus.dev_dataset(nlp, gold_preproc=gold_preproc))
     begin = timer()
     scorer = nlp.evaluate(dev_dataset, verbose=False)
     end = timer()
-    nwords = sum(len(ex.doc) for ex in dev_dataset)
+    nwords = sum(len(ex.predicted) for ex in dev_dataset)
     results = {
         "Time": f"{end - begin:.2f} s",
         "Words": nwords,
@@ -90,10 +89,22 @@ def evaluate(
         "Sent R": f"{scorer.sent_r:.2f}",
         "Sent F": f"{scorer.sent_f:.2f}",
     }
+    data = {re.sub(r"[\s/]", "_", k.lower()): v for k, v in results.items()}
+
     msg.table(results, title="Results")
 
+    if scorer.ents_per_type:
+        data["ents_per_type"] = scorer.ents_per_type
+        print_ents_per_type(msg, scorer.ents_per_type)
+    if scorer.textcats_f_per_cat:
+        data["textcats_f_per_cat"] = scorer.textcats_f_per_cat
+        print_textcats_f_per_cat(msg, scorer.textcats_f_per_cat)
+    if scorer.textcats_auc_per_cat:
+        data["textcats_auc_per_cat"] = scorer.textcats_auc_per_cat
+        print_textcats_auc_per_cat(msg, scorer.textcats_auc_per_cat)
+
     if displacy_path:
-        docs = [ex.doc for ex in dev_dataset]
+        docs = [ex.predicted for ex in dev_dataset]
         render_deps = "parser" in nlp.meta.get("pipeline", [])
         render_ents = "ner" in nlp.meta.get("pipeline", [])
         render_parses(
@@ -105,8 +116,11 @@ def evaluate(
             ents=render_ents,
         )
         msg.good(f"Generated {displacy_limit} parses as HTML", displacy_path)
-    if return_scores:
+
-        return scorer.scores
+    if output_path is not None:
+        srsly.write_json(output_path, data)
+        msg.good(f"Saved results to {output_path}")
+    return data
 
 
 def render_parses(
@@ -128,3 +142,40 @@ def render_parses(
         )
         with (output_path / "parses.html").open("w", encoding="utf8") as file_:
             file_.write(html)
+
+
+def print_ents_per_type(msg: Printer, scores: Dict[str, Dict[str, float]]) -> None:
+    data = [
+        (k, f"{v['p']:.2f}", f"{v['r']:.2f}", f"{v['f']:.2f}")
+        for k, v in scores.items()
+    ]
+    msg.table(
+        data,
+        header=("", "P", "R", "F"),
+        aligns=("l", "r", "r", "r"),
+        title="NER (per type)",
+    )
+
+
+def print_textcats_f_per_cat(msg: Printer, scores: Dict[str, Dict[str, float]]) -> None:
+    data = [
+        (k, f"{v['p']:.2f}", f"{v['r']:.2f}", f"{v['f']:.2f}")
+        for k, v in scores.items()
+    ]
+    msg.table(
+        data,
+        header=("", "P", "R", "F"),
+        aligns=("l", "r", "r", "r"),
+        title="Textcat F (per type)",
+    )
+
+
+def print_textcats_auc_per_cat(
+    msg: Printer, scores: Dict[str, Dict[str, float]]
+) -> None:
+    msg.table(
+        [(k, f"{v['roc_auc_score']:.2f}") for k, v in scores.items()],
+        header=("", "ROC AUC"),
+        aligns=("l", "r"),
+        title="Textcat ROC AUC (per label)",
+    )

spacy/cli/package.py

@@ -16,8 +16,9 @@ def package_cli(
     # fmt: off
     input_dir: Path = Arg(..., help="Directory with model data", exists=True, file_okay=False),
     output_dir: Path = Arg(..., help="Output parent directory", exists=True, file_okay=False),
-    meta_path: Optional[Path] = Opt(None, "--meta-path", "-m", help="Path to meta.json", exists=True, dir_okay=False),
+    meta_path: Optional[Path] = Opt(None, "--meta-path", "--meta", "-m", help="Path to meta.json", exists=True, dir_okay=False),
     create_meta: bool = Opt(False, "--create-meta", "-c", "-C", help="Create meta.json, even if one exists"),
+    version: Optional[str] = Opt(None, "--version", "-v", help="Package version to override meta"),
     force: bool = Opt(False, "--force", "-f", "-F", help="Force overwriting existing model in output directory"),
     # fmt: on
 ):
@@ -32,6 +33,7 @@ def package_cli(
         input_dir,
         output_dir,
         meta_path=meta_path,
+        version=version,
         create_meta=create_meta,
         force=force,
         silent=False,
@@ -42,6 +44,7 @@ def package(
     input_dir: Path,
     output_dir: Path,
     meta_path: Optional[Path] = None,
+    version: Optional[str] = None,
     create_meta: bool = False,
     force: bool = False,
     silent: bool = True,
@@ -61,10 +64,13 @@ def package(
     if not meta_path.exists() or not meta_path.is_file():
         msg.fail("Can't load model meta.json", meta_path, exits=1)
     meta = srsly.read_json(meta_path)
+    meta = get_meta(input_dir, meta)
+    if version is not None:
+        meta["version"] = version
     if not create_meta:  # only print if user doesn't want to overwrite
         msg.good("Loaded meta.json from file", meta_path)
     else:
-        meta = generate_meta(input_dir, meta, msg)
+        meta = generate_meta(meta, msg)
     errors = validate(ModelMetaSchema, meta)
     if errors:
         msg.fail("Invalid model meta.json", "\n".join(errors), exits=1)
@@ -101,20 +107,20 @@ def create_file(file_path: Path, contents: str) -> None:
     file_path.open("w", encoding="utf-8").write(contents)
 
 
-def generate_meta(
+def get_meta(
-    model_path: Union[str, Path], existing_meta: Dict[str, Any], msg: Printer
+    model_path: Union[str, Path], existing_meta: Dict[str, Any]
 ) -> Dict[str, Any]:
-    meta = existing_meta or {}
+    meta = {
-    settings = [
+        "lang": "en",
-        ("lang", "Model language", meta.get("lang", "en")),
+        "name": "model",
-        ("name", "Model name", meta.get("name", "model")),
+        "version": "0.0.0",
-        ("version", "Model version", meta.get("version", "0.0.0")),
+        "description": None,
-        ("description", "Model description", meta.get("description", False)),
+        "author": None,
-        ("author", "Author", meta.get("author", False)),
+        "email": None,
-        ("email", "Author email", meta.get("email", False)),
+        "url": None,
-        ("url", "Author website", meta.get("url", False)),
+        "license": "MIT",
-        ("license", "License", meta.get("license", "MIT")),
+    }
-    ]
+    meta.update(existing_meta)
     nlp = util.load_model_from_path(Path(model_path))
     meta["spacy_version"] = util.get_model_version_range(about.__version__)
     meta["pipeline"] = nlp.pipe_names
@@ -124,6 +130,23 @@ def generate_meta(
         "keys": nlp.vocab.vectors.n_keys,
         "name": nlp.vocab.vectors.name,
     }
+    if about.__title__ != "spacy":
+        meta["parent_package"] = about.__title__
+    return meta
+
+
+def generate_meta(existing_meta: Dict[str, Any], msg: Printer) -> Dict[str, Any]:
+    meta = existing_meta or {}
+    settings = [
+        ("lang", "Model language", meta.get("lang", "en")),
+        ("name", "Model name", meta.get("name", "model")),
+        ("version", "Model version", meta.get("version", "0.0.0")),
+        ("description", "Model description", meta.get("description", None)),
+        ("author", "Author", meta.get("author", None)),
+        ("email", "Author email", meta.get("email", None)),
+        ("url", "Author website", meta.get("url", None)),
+        ("license", "License", meta.get("license", "MIT")),
+    ]
     msg.divider("Generating meta.json")
     msg.text(
         "Enter the package settings for your model. The following information "
@@ -132,8 +155,6 @@ def generate_meta(
     for setting, desc, default in settings:
         response = get_raw_input(desc, default)
         meta[setting] = default if response == "" and default else response
-    if about.__title__ != "spacy":
-        meta["parent_package"] = about.__title__
     return meta
 
 
@@ -184,12 +205,12 @@ def setup_package():
 
     setup(
         name=model_name,
-        description=meta['description'],
+        description=meta.get('description'),
-        author=meta['author'],
+        author=meta.get('author'),
-        author_email=meta['email'],
+        author_email=meta.get('email'),
-        url=meta['url'],
+        url=meta.get('url'),
         version=meta['version'],
-        license=meta['license'],
+        license=meta.get('license'),
         packages=[model_name],
         package_data={model_name: list_files(model_dir)},
         install_requires=list_requirements(meta),

spacy/cli/project.py

@@ -0,0 +1,679 @@
+from typing import List, Dict, Any, Optional, Sequence
+import typer
+import srsly
+from pathlib import Path
+from wasabi import msg
+import subprocess
+import shlex
+import os
+import re
+import shutil
+import sys
+import requests
+import tqdm
+
+from ._app import app, Arg, Opt, COMMAND, NAME
+from .. import about
+from ..schemas import ProjectConfigSchema, validate
+from ..util import ensure_path, run_command, make_tempdir, working_dir
+from ..util import get_hash, get_checksum
+
+
+CONFIG_FILE = "project.yml"
+DVC_CONFIG = "dvc.yaml"
+DIRS = [
+    "assets",
+    "metas",
+    "configs",
+    "packages",
+    "metrics",
+    "scripts",
+    "notebooks",
+    "training",
+    "corpus",
+]
+CACHES = [
+    Path.home() / ".torch",
+    Path.home() / ".caches" / "torch",
+    os.environ.get("TORCH_HOME"),
+    Path.home() / ".keras",
+]
+DVC_CONFIG_COMMENT = """# This file is auto-generated by spaCy based on your project.yml. Do not edit
+# it directly and edit the project.yml instead and re-run the project."""
+CLI_HELP = f"""Command-line interface for spaCy projects and working with project
+templates. You'd typically start by cloning a project template to a local
+directory and fetching its assets like datasets etc. See the project's
+{CONFIG_FILE} for the available commands. Under the hood, spaCy uses DVC (Data
+Version Control) to manage input and output files and to ensure steps are only
+re-run if their inputs change.
+"""
+
+project_cli = typer.Typer(help=CLI_HELP)
+
+
+@project_cli.callback(invoke_without_command=True)
+def callback(ctx: typer.Context):
+    """This runs before every project command and ensures DVC is installed."""
+    ensure_dvc()
+
+
+################
+# CLI COMMANDS #
+################
+
+
+@project_cli.command("clone")
+def project_clone_cli(
+    # fmt: off
+    name: str = Arg(..., help="The name of the template to fetch"),
+    dest: Path = Arg(Path.cwd(), help="Where to download and work. Defaults to current working directory.", exists=False),
+    repo: str = Opt(about.__projects__, "--repo", "-r", help="The repository to look in."),
+    git: bool = Opt(False, "--git", "-G", help="Initialize project as a Git repo"),
+    no_init: bool = Opt(False, "--no-init", "-NI", help="Don't initialize the project with DVC"),
+    # fmt: on
+):
+    """Clone a project template from a repository. Calls into "git" and will
+    only download the files from the given subdirectory. The GitHub repo
+    defaults to the official spaCy template repo, but can be customized
+    (including using a private repo). Setting the --git flag will also
+    initialize the project directory as a Git repo. If the project is intended
+    to be a Git repo, it should be initialized with Git first, before
+    initializing DVC (Data Version Control). This allows DVC to integrate with
+    Git.
+    """
+    project_clone(name, dest, repo=repo, git=git, no_init=no_init)
+
+
+@project_cli.command("init")
+def project_init_cli(
+    path: Path = Arg(..., help="Path to cloned project", exists=True, file_okay=False),
+    git: bool = Opt(False, "--git", "-G", help="Initialize project as a Git repo"),
+):
+    """Initialize a project directory with DVC and optionally Git. This should
+    typically be taken care of automatically when you run the "project clone"
+    command, but you can also run it separately. If the project is intended to
+    be a Git repo, it should be initialized with Git first, before initializing
+    DVC. This allows DVC to integrate with Git.
+    """
+    project_init(path, git=git, silent=True)
+
+
+@project_cli.command("assets")
+def project_assets_cli(
+    # fmt: off
+    project_dir: Path = Arg(..., help="Path to cloned project", exists=True, file_okay=False),
+    # fmt: on
+):
+    """Use DVC (Data Version Control) to fetch project assets. Assets are
+    defined in the "assets" section of the project config. If possible, DVC
+    will try to track the files so you can pull changes from upstream. It will
+    also try and store the checksum so the assets are versioned. If th file
+    can't be tracked or checked, it will be downloaded without DVC. If a checksum
+    is provided in the project config, the file is only downloaded if no local
+    file with the same checksum exists.
+    """
+    project_assets(project_dir)
+
+
+@project_cli.command(
+    "run-all",
+    context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
+)
+def project_run_all_cli(
+    # fmt: off
+    ctx: typer.Context,
+    project_dir: Path = Arg(..., help="Location of project directory", exists=True, file_okay=False),
+    show_help: bool = Opt(False, "--help", help="Show help message and available subcommands")
+    # fmt: on
+):
+    """Run all commands defined in the project. This command will use DVC and
+    the defined outputs and dependencies in the project config to determine
+    which steps need to be re-run and where to start. This means you're only
+    re-generating data if the inputs have changed.
+
+    This command calls into "dvc repro" and all additional arguments are passed
+    to the "dvc repro" command: https://dvc.org/doc/command-reference/repro
+    """
+    if show_help:
+        print_run_help(project_dir)
+    else:
+        project_run_all(project_dir, *ctx.args)
+
+
+@project_cli.command(
+    "run", context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
+)
+def project_run_cli(
+    # fmt: off
+    ctx: typer.Context,
+    project_dir: Path = Arg(..., help="Location of project directory", exists=True, file_okay=False),
+    subcommand: str = Arg(None, help="Name of command defined in project config"),
+    show_help: bool = Opt(False, "--help", help="Show help message and available subcommands")
+    # fmt: on
+):
+    """Run a named script defined in the project config. If the command is
+    part of the default pipeline defined in the "run" section, DVC is used to
+    determine whether the step should re-run if its inputs have changed, or
+    whether everything is up to date. If the script is not part of the default
+    pipeline, it will be called separately without DVC.
+
+    If DVC is used, the command calls into "dvc repro" and all additional
+    arguments are passed to the "dvc repro" command:
+    https://dvc.org/doc/command-reference/repro
+    """
+    if show_help or not subcommand:
+        print_run_help(project_dir, subcommand)
+    else:
+        project_run(project_dir, subcommand, *ctx.args)
+
+
+@project_cli.command("exec", hidden=True)
+def project_exec_cli(
+    # fmt: off
+    project_dir: Path = Arg(..., help="Location of project directory", exists=True, file_okay=False),
+    subcommand: str = Arg(..., help="Name of command defined in project config"),
+    # fmt: on
+):
+    """Execute a command defined in the project config. This CLI command is
+    only called internally in auto-generated DVC pipelines, as a shortcut for
+    multi-step commands in the project config. You typically shouldn't have to
+    call it yourself. To run a command, call "run" or "run-all".
+    """
+    project_exec(project_dir, subcommand)
+
+
+@project_cli.command("update-dvc")
+def project_update_dvc_cli(
+    # fmt: off
+    project_dir: Path = Arg(..., help="Location of project directory", exists=True, file_okay=False),
+    verbose: bool = Opt(False, "--verbose", "-V", help="Print more info"),
+    force: bool = Opt(False, "--force", "-F", help="Force update DVC config"),
+    # fmt: on
+):
+    """Update the auto-generated DVC config file. Uses the steps defined in the
+    "run" section of the project config. This typically happens automatically
+    when running a command, but can also be triggered manually if needed.
+    """
+    config = load_project_config(project_dir)
+    updated = update_dvc_config(project_dir, config, verbose=verbose, force=force)
+    if updated:
+        msg.good(f"Updated DVC config from {CONFIG_FILE}")
+    else:
+        msg.info(f"No changes found in {CONFIG_FILE}, no update needed")
+
+
+app.add_typer(project_cli, name="project")
+
+
+#################
+# CLI FUNCTIONS #
+#################
+
+
+def project_clone(
+    name: str,
+    dest: Path,
+    *,
+    repo: str = about.__projects__,
+    git: bool = False,
+    no_init: bool = False,
+) -> None:
+    """Clone a project template from a repository.
+
+    name (str): Name of subdirectory to clone.
+    dest (Path): Destination path of cloned project.
+    repo (str): URL of Git repo containing project templates.
+    git (bool): Initialize project as Git repo. Should be set to True if project
+        is intended as a repo, since it will allow DVC to integrate with Git.
+    no_init (bool): Don't initialize DVC and Git automatically. If True, the
+        "init" command or "git init" and "dvc init" need to be run manually.
+    """
+    dest = ensure_path(dest)
+    check_clone(name, dest, repo)
+    project_dir = dest.resolve()
+    # We're using Git and sparse checkout to only clone the files we need
+    with make_tempdir() as tmp_dir:
+        cmd = f"git clone {repo} {tmp_dir} --no-checkout --depth 1 --config core.sparseCheckout=true"
+        run_command(shlex.split(cmd))
+        with (tmp_dir / ".git" / "info" / "sparse-checkout").open("w") as f:
+            f.write(name)
+        run_command(["git", "-C", tmp_dir, "fetch"])
+        run_command(["git", "-C", tmp_dir, "checkout"])
+        shutil.move(str(tmp_dir / Path(name).name), str(project_dir))
+    msg.good(f"Cloned project '{name}' from {repo}")
+    for sub_dir in DIRS:
+        dir_path = project_dir / sub_dir
+        if not dir_path.exists():
+            dir_path.mkdir(parents=True)
+    if not no_init:
+        project_init(project_dir, git=git, silent=True)
+    msg.good(f"Your project is now ready!", dest)
+    print(f"To fetch the assets, run:\n{COMMAND} project assets {dest}")
+
+
+def project_init(
+    project_dir: Path,
+    *,
+    git: bool = False,
+    silent: bool = False,
+    analytics: bool = False,
+):
+    """Initialize a project as a DVC and (optionally) as a Git repo.
+
+    project_dir (Path): Path to project directory.
+    git (bool): Also call "git init" to initialize directory as a Git repo.
+    silent (bool): Don't print any output (via DVC).
+    analytics (bool): Opt-in to DVC analytics (defaults to False).
+    """
+    with working_dir(project_dir):
+        init_cmd = ["dvc", "init"]
+        if silent:
+            init_cmd.append("--quiet")
+        if not git:
+            init_cmd.append("--no-scm")
+        if git:
+            run_command(["git", "init"])
+        run_command(init_cmd)
+        # We don't want to have analytics on by default – our users should
+        # opt-in explicitly. If they want it, they can always enable it.
+        if not analytics:
+            run_command(["dvc", "config", "core.analytics", "false"])
+        config = load_project_config(project_dir)
+        setup_check_dvc(project_dir, config)
+
+
+def project_assets(project_dir: Path) -> None:
+    """Fetch assets for a project using DVC if possible.
+
+    project_dir (Path): Path to project directory.
+    """
+    project_path = ensure_path(project_dir)
+    config = load_project_config(project_path)
+    setup_check_dvc(project_path, config)
+    assets = config.get("assets", {})
+    if not assets:
+        msg.warn(f"No assets specified in {CONFIG_FILE}", exits=0)
+    msg.info(f"Fetching {len(assets)} asset(s)")
+    variables = config.get("variables", {})
+    fetched_assets = []
+    for asset in assets:
+        url = asset["url"].format(**variables)
+        dest = asset["dest"].format(**variables)
+        fetched_path = fetch_asset(project_path, url, dest, asset.get("checksum"))
+        if fetched_path:
+            fetched_assets.append(str(fetched_path))
+    if fetched_assets:
+        with working_dir(project_path):
+            run_command(["dvc", "add", *fetched_assets, "--external"])
+
+
+def fetch_asset(
+    project_path: Path, url: str, dest: Path, checksum: Optional[str] = None
+) -> Optional[Path]:
+    """Fetch an asset from a given URL or path. Will try to import the file
+    using DVC's import-url if possible (fully tracked and versioned) and falls
+    back to get-url (versioned) and a non-DVC download if necessary. If a
+    checksum is provided and a local file exists, it's only re-downloaded if the
+    checksum doesn't match.
+
+    project_path (Path): Path to project directory.
+    url (str): URL or path to asset.
+    checksum (Optional[str]): Optional expected checksum of local file.
+    RETURNS (Optional[Path]): The path to the fetched asset or None if fetching
+        the asset failed.
+    """
+    url = convert_asset_url(url)
+    dest_path = (project_path / dest).resolve()
+    if dest_path.exists() and checksum:
+        # If there's already a file, check for checksum
+        # TODO: add support for caches (dvc import-url with local path)
+        if checksum == get_checksum(dest_path):
+            msg.good(f"Skipping download with matching checksum: {dest}")
+            return dest_path
+    with working_dir(project_path):
+        try:
+            # If these fail, we don't want to output an error or info message.
+            # Try with tracking the source first, then just downloading with
+            # DVC, then a regular non-DVC download.
+            try:
+                dvc_cmd = ["dvc", "import-url", url, str(dest_path)]
+                print(subprocess.check_output(dvc_cmd, stderr=subprocess.DEVNULL))
+            except subprocess.CalledProcessError:
+                dvc_cmd = ["dvc", "get-url", url, str(dest_path)]
+                print(subprocess.check_output(dvc_cmd, stderr=subprocess.DEVNULL))
+        except subprocess.CalledProcessError:
+            try:
+                download_file(url, dest_path)
+            except requests.exceptions.HTTPError as e:
+                msg.fail(f"Download failed: {dest}", e)
+                return None
+    if checksum and checksum != get_checksum(dest_path):
+        msg.warn(f"Checksum doesn't match value defined in {CONFIG_FILE}: {dest}")
+    msg.good(f"Fetched asset {dest}")
+    return dest_path
+
+
+def project_run_all(project_dir: Path, *dvc_args) -> None:
+    """Run all commands defined in the project using DVC.
+
+    project_dir (Path): Path to project directory.
+    *dvc_args: Other arguments passed to "dvc repro".
+    """
+    config = load_project_config(project_dir)
+    setup_check_dvc(project_dir, config)
+    dvc_cmd = ["dvc", "repro", *dvc_args]
+    with working_dir(project_dir):
+        run_command(dvc_cmd)
+
+
+def print_run_help(project_dir: Path, subcommand: Optional[str] = None) -> None:
+    """Simulate a CLI help prompt using the info available in the project config.
+
+    project_dir (Path): The project directory.
+    subcommand (Optional[str]): The subcommand or None. If a subcommand is
+        provided, the subcommand help is shown. Otherwise, the top-level help
+        and a list of available commands is printed.
+    """
+    config = load_project_config(project_dir)
+    setup_check_dvc(project_dir, config)
+    config_commands = config.get("commands", [])
+    commands = {cmd["name"]: cmd for cmd in config_commands}
+    if subcommand:
+        validate_subcommand(commands.keys(), subcommand)
+        print(f"Usage: {COMMAND} project run {project_dir} {subcommand}")
+        help_text = commands[subcommand].get("help")
+        if help_text:
+            msg.text(f"\n{help_text}\n")
+    else:
+        print(f"\nAvailable commands in {CONFIG_FILE}")
+        print(f"Usage: {COMMAND} project run {project_dir} [COMMAND]")
+        msg.table([(cmd["name"], cmd.get("help", "")) for cmd in config_commands])
+        msg.text("Run all commands defined in the 'run' block of the project config:")
+        print(f"{COMMAND} project run-all {project_dir}")
+
+
+def project_run(project_dir: Path, subcommand: str, *dvc_args) -> None:
+    """Run a named script defined in the project config. If the script is part
+    of the default pipeline (defined in the "run" section), DVC is used to
+    execute the command, so it can determine whether to rerun it. It then
+    calls into "exec" to execute it.
+
+    project_dir (Path): Path to project directory.
+    subcommand (str): Name of command to run.
+    *dvc_args: Other arguments passed to "dvc repro".
+    """
+    config = load_project_config(project_dir)
+    setup_check_dvc(project_dir, config)
+    config_commands = config.get("commands", [])
+    variables = config.get("variables", {})
+    commands = {cmd["name"]: cmd for cmd in config_commands}
+    validate_subcommand(commands.keys(), subcommand)
+    if subcommand in config.get("run", []):
+        # This is one of the pipeline commands tracked in DVC
+        dvc_cmd = ["dvc", "repro", subcommand, *dvc_args]
+        with working_dir(project_dir):
+            run_command(dvc_cmd)
+    else:
+        cmd = commands[subcommand]
+        # Deps in non-DVC commands aren't tracked, but if they're defined,
+        # make sure they exist before running the command
+        for dep in cmd.get("deps", []):
+            if not (project_dir / dep).exists():
+                err = f"Missing dependency specified by command '{subcommand}': {dep}"
+                msg.fail(err, exits=1)
+        with working_dir(project_dir):
+            run_commands(cmd["script"], variables)
+
+
+def project_exec(project_dir: Path, subcommand: str):
+    """Execute a command defined in the project config.
+
+    project_dir (Path): Path to project directory.
+    subcommand (str): Name of command to run.
+    """
+    config = load_project_config(project_dir)
+    config_commands = config.get("commands", [])
+    variables = config.get("variables", {})
+    commands = {cmd["name"]: cmd for cmd in config_commands}
+    with working_dir(project_dir):
+        run_commands(commands[subcommand]["script"], variables)
+
+
+###########
+# HELPERS #
+###########
+
+
+def load_project_config(path: Path) -> Dict[str, Any]:
+    """Load the project config file from a directory and validate it.
+
+    path (Path): The path to the project directory.
+    RETURNS (Dict[str, Any]): The loaded project config.
+    """
+    config_path = path / CONFIG_FILE
+    if not config_path.exists():
+        msg.fail("Can't find project config", config_path, exits=1)
+    invalid_err = f"Invalid project config in {CONFIG_FILE}"
+    try:
+        config = srsly.read_yaml(config_path)
+    except ValueError as e:
+        msg.fail(invalid_err, e, exits=1)
+    errors = validate(ProjectConfigSchema, config)
+    if errors:
+        msg.fail(invalid_err, "\n".join(errors), exits=1)
+    return config
+
+
+def update_dvc_config(
+    path: Path,
+    config: Dict[str, Any],
+    verbose: bool = False,
+    silent: bool = False,
+    force: bool = False,
+) -> bool:
+    """Re-run the DVC commands in dry mode and update dvc.yaml file in the
+    project directory. The file is auto-generated based on the config. The
+    first line of the auto-generated file specifies the hash of the config
+    dict, so if any of the config values change, the DVC config is regenerated.
+
+    path (Path): The path to the project directory.
+    config (Dict[str, Any]): The loaded project config.
+    verbose (bool): Whether to print additional info (via DVC).
+    silent (bool): Don't output anything (via DVC).
+    force (bool): Force update, even if hashes match.
+    RETURNS (bool): Whether the DVC config file was updated.
+    """
+    config_hash = get_hash(config)
+    path = path.resolve()
+    dvc_config_path = path / DVC_CONFIG
+    if dvc_config_path.exists():
+        # Cneck if the file was generated using the current config, if not, redo
+        with dvc_config_path.open("r", encoding="utf8") as f:
+            ref_hash = f.readline().strip().replace("# ", "")
+        if ref_hash == config_hash and not force:
+            return False  # Nothing has changed in project config, don't need to update
+        dvc_config_path.unlink()
+    variables = config.get("variables", {})
+    commands = []
+    # We only want to include commands that are part of the main list of "run"
+    # commands in project.yml and should be run in sequence
+    config_commands = {cmd["name"]: cmd for cmd in config.get("commands", [])}
+    for name in config.get("run", []):
+        validate_subcommand(config_commands.keys(), name)
+        command = config_commands[name]
+        deps = command.get("deps", [])
+        outputs = command.get("outputs", [])
+        outputs_no_cache = command.get("outputs_no_cache", [])
+        if not deps and not outputs and not outputs_no_cache:
+            continue
+        # Default to "." as the project path since dvc.yaml is auto-generated
+        # and we don't want arbitrary paths in there
+        project_cmd = ["python", "-m", NAME, "project", "exec", ".", name]
+        deps_cmd = [c for cl in [["-d", p] for p in deps] for c in cl]
+        outputs_cmd = [c for cl in [["-o", p] for p in outputs] for c in cl]
+        outputs_nc_cmd = [c for cl in [["-O", p] for p in outputs_no_cache] for c in cl]
+        dvc_cmd = ["dvc", "run", "-n", name, "-w", str(path), "--no-exec"]
+        if verbose:
+            dvc_cmd.append("--verbose")
+        if silent:
+            dvc_cmd.append("--quiet")
+        full_cmd = [*dvc_cmd, *deps_cmd, *outputs_cmd, *outputs_nc_cmd, *project_cmd]
+        commands.append(" ".join(full_cmd))
+    with working_dir(path):
+        run_commands(commands, variables, silent=True)
+    with dvc_config_path.open("r+", encoding="utf8") as f:
+        content = f.read()
+        f.seek(0, 0)
+        f.write(f"# {config_hash}\n{DVC_CONFIG_COMMENT}\n{content}")
+    return True
+
+
+def ensure_dvc() -> None:
+    """Ensure that the "dvc" command is available and show an error if not."""
+    try:
+        subprocess.run(["dvc", "--version"], stdout=subprocess.DEVNULL)
+    except Exception:
+        msg.fail(
+            "spaCy projects require DVC (Data Version Control) and the 'dvc' command",
+            "You can install the Python package from pip (pip install dvc) or "
+            "conda (conda install -c conda-forge dvc). For more details, see the "
+            "documentation: https://dvc.org/doc/install",
+            exits=1,
+        )
+
+
+def setup_check_dvc(project_dir: Path, config: Dict[str, Any]) -> None:
+    """Check that the project is set up correctly with DVC and update its
+    config if needed. Will raise an error if the project is not an initialized
+    DVC project.
+
+    project_dir (Path): The path to the project directory.
+    config (Dict[str, Any]): The loaded project config.
+    """
+    if not project_dir.exists():
+        msg.fail(f"Can't find project directory: {project_dir}")
+    if not (project_dir / ".dvc").exists():
+        msg.fail(
+            "Project not initialized as a DVC project.",
+            f"Make sure that the project template was cloned correctly. To "
+            f"initialize the project directory manually, you can run: "
+            f"{COMMAND} project init {project_dir}",
+            exits=1,
+        )
+    with msg.loading("Updating DVC config..."):
+        updated = update_dvc_config(project_dir, config, silent=True)
+    if updated:
+        msg.good(f"Updated DVC config from changed {CONFIG_FILE}")
+
+
+def run_commands(
+    commands: List[str] = tuple(), variables: Dict[str, str] = {}, silent: bool = False
+) -> None:
+    """Run a sequence of commands in a subprocess, in order.
+
+    commands (List[str]): The split commands.
+    variables (Dict[str, str]): Dictionary of variable names, mapped to their
+        values. Will be used to substitute format string variables in the
+        commands.
+    silent (boll): Don't print the commands.
+    """
+    for command in commands:
+        # Substitute variables, e.g. "./{NAME}.json"
+        command = command.format(**variables)
+        command = shlex.split(command)
+        # TODO: is this needed / a good idea?
+        if len(command) and command[0] == "python":
+            command[0] = sys.executable
+        elif len(command) and command[0] == "pip":
+            command = [sys.executable, "-m", "pip", *command[1:]]
+        if not silent:
+            print(" ".join(command))
+        run_command(command)
+
+
+def convert_asset_url(url: str) -> str:
+    """Check and convert the asset URL if needed.
+
+    url (str): The asset URL.
+    RETURNS (str): The converted URL.
+    """
+    # If the asset URL is a regular GitHub URL it's likely a mistake
+    if re.match("(http(s?)):\/\/github.com", url):
+        converted = url.replace("github.com", "raw.githubusercontent.com")
+        converted = re.sub(r"/(tree|blob)/", "/", converted)
+        msg.warn(
+            "Downloading from a regular GitHub URL. This will only download "
+            "the source of the page, not the actual file. Converting the URL "
+            "to a raw URL.",
+            converted,
+        )
+        return converted
+    return url
+
+
+def check_clone(name: str, dest: Path, repo: str) -> None:
+    """Check and validate that the destination path can be used to clone. Will
+    check that Git is available and that the destination path is suitable.
+
+    name (str): Name of the directory to clone from the repo.
+    dest (Path): Local destination of cloned directory.
+    repo (str): URL of the repo to clone from.
+    """
+    try:
+        subprocess.run(["git", "--version"], stdout=subprocess.DEVNULL)
+    except Exception:
+        msg.fail(
+            f"Cloning spaCy project templates requires Git and the 'git' command. ",
+            f"To clone a project without Git, copy the files from the '{name}' "
+            f"directory in the {repo} to {dest} manually and then run:",
+            f"{COMMAND} project init {dest}",
+            exits=1,
+        )
+    if not dest:
+        msg.fail(f"Not a valid directory to clone project: {dest}", exits=1)
+    if dest.exists():
+        # Directory already exists (not allowed, clone needs to create it)
+        msg.fail(f"Can't clone project, directory already exists: {dest}", exits=1)
+    if not dest.parent.exists():
+        # We're not creating parents, parent dir should exist
+        msg.fail(
+            f"Can't clone project, parent directory doesn't exist: {dest.parent}",
+            exits=1,
+        )
+
+
+def validate_subcommand(commands: Sequence[str], subcommand: str) -> None:
+    """Check that a subcommand is valid and defined. Raises an error otherwise.
+
+    commands (Sequence[str]): The available commands.
+    subcommand (str): The subcommand.
+    """
+    if subcommand not in commands:
+        msg.fail(
+            f"Can't find command '{subcommand}' in {CONFIG_FILE}. "
+            f"Available commands: {', '.join(commands)}",
+            exits=1,
+        )
+
+
+def download_file(url: str, dest: Path, chunk_size: int = 1024) -> None:
+    """Download a file using requests.
+
+    url (str): The URL of the file.
+    dest (Path): The destination path.
+    chunk_size (int): The size of chunks to read/write.
+    """
+    response = requests.get(url, stream=True)
+    response.raise_for_status()
+    total = int(response.headers.get("content-length", 0))
+    progress_settings = {
+        "total": total,
+        "unit": "iB",
+        "unit_scale": True,
+        "unit_divisor": chunk_size,
+        "leave": False,
+    }
+    with dest.open("wb") as f, tqdm.tqdm(**progress_settings) as bar:
+        for data in response.iter_content(chunk_size=chunk_size):
+            size = f.write(data)
+            bar.update(size)

spacy/errors.py

@@ -132,6 +132,7 @@ class Warnings(object):
             "are currently: da, de, el, en, id, lb, pt, ru, sr, ta, th.")
 
     # TODO: fix numbering after merging develop into master
+    W092 = ("Ignoring annotations for sentence starts, as dependency heads are set.")
     W093 = ("Could not find any data to train the {name} on. Is your "
             "input data correctly formatted ?")
     W094 = ("Model '{model}' ({model_version}) specifies an under-constrained "
@@ -154,7 +155,7 @@ class Warnings(object):
             "so a default configuration was used.")
     W099 = ("Expected 'dict' type for the 'model' argument of pipe '{pipe}', "
             "but got '{type}' instead, so ignoring it.")
-    W100 = ("Skipping unsupported morphological feature(s): {feature}. "
+    W100 = ("Skipping unsupported morphological feature(s): '{feature}'. "
             "Provide features as a dict {{\"Field1\": \"Value1,Value2\"}} or "
             "string \"Field1=Value1,Value2|Field2=Value3\".")
 
@@ -182,18 +183,13 @@ class Errors(object):
             "`nlp.select_pipes()`, you should remove them explicitly with "
             "`nlp.remove_pipe()` before the pipeline is restored. Names of "
             "the new components: {names}")
-    E009 = ("The `update` method expects same number of docs and golds, but "
-            "got: {n_docs} docs, {n_golds} golds.")
     E010 = ("Word vectors set to length 0. This may be because you don't have "
             "a model installed or loaded, or because your model doesn't "
             "include word vectors. For more info, see the docs:\n"
             "https://spacy.io/usage/models")
     E011 = ("Unknown operator: '{op}'. Options: {opts}")
     E012 = ("Cannot add pattern for zero tokens to matcher.\nKey: {key}")
-    E013 = ("Error selecting action in matcher")
     E014 = ("Unknown tag ID: {tag}")
-    E015 = ("Conflicting morphology exception for ({tag}, {orth}). Use "
-            "`force=True` to overwrite.")
     E016 = ("MultitaskObjective target should be function or one of: dep, "
             "tag, ent, dep_tag_offset, ent_tag.")
     E017 = ("Can only add unicode or bytes. Got type: {value_type}")
@@ -201,21 +197,8 @@ class Errors(object):
             "refers to an issue with the `Vocab` or `StringStore`.")
     E019 = ("Can't create transition with unknown action ID: {action}. Action "
             "IDs are enumerated in spacy/syntax/{src}.pyx.")
-    E020 = ("Could not find a gold-standard action to supervise the "
-            "dependency parser. The tree is non-projective (i.e. it has "
-            "crossing arcs - see spacy/syntax/nonproj.pyx for definitions). "
-            "The ArcEager transition system only supports projective trees. "
-            "To learn non-projective representations, transform the data "
-            "before training and after parsing. Either pass "
-            "`make_projective=True` to the GoldParse class, or use "
-            "spacy.syntax.nonproj.preprocess_training_data.")
-    E021 = ("Could not find a gold-standard action to supervise the "
-            "dependency parser. The GoldParse was projective. The transition "
-            "system has {n_actions} actions. State at failure: {state}")
     E022 = ("Could not find a transition with the name '{name}' in the NER "
             "model.")
-    E023 = ("Error cleaning up beam: The same state occurred twice at "
-            "memory address {addr} and position {i}.")
     E024 = ("Could not find an optimal move to supervise the parser. Usually, "
             "this means that the model can't be updated in a way that's valid "
             "and satisfies the correct annotations specified in the GoldParse. "
@@ -259,7 +242,6 @@ class Errors(object):
             "offset {start}.")
     E037 = ("Error calculating span: Can't find a token ending at character "
             "offset {end}.")
-    E038 = ("Error finding sentence for span. Infinite loop detected.")
     E039 = ("Array bounds exceeded while searching for root word. This likely "
             "means the parse tree is in an invalid state. Please report this "
             "issue here: http://github.com/explosion/spaCy/issues")
@@ -290,8 +272,6 @@ class Errors(object):
     E059 = ("One (and only one) keyword arg must be set. Got: {kwargs}")
     E060 = ("Cannot add new key to vectors: the table is full. Current shape: "
             "({rows}, {cols}).")
-    E061 = ("Bad file name: {filename}. Example of a valid file name: "
-            "'vectors.128.f.bin'")
     E062 = ("Cannot find empty bit for new lexical flag. All bits between 0 "
             "and 63 are occupied. You can replace one by specifying the "
             "`flag_id` explicitly, e.g. "
@@ -305,39 +285,17 @@ class Errors(object):
             "Query string: {string}\nOrth cached: {orth}\nOrth ID: {orth_id}")
     E065 = ("Only one of the vector table's width and shape can be specified. "
             "Got width {width} and shape {shape}.")
-    E066 = ("Error creating model helper for extracting columns. Can only "
-            "extract columns by positive integer. Got: {value}.")
     E067 = ("Invalid BILUO tag sequence: Got a tag starting with 'I' (inside "
             "an entity) without a preceding 'B' (beginning of an entity). "
             "Tag sequence:\n{tags}")
     E068 = ("Invalid BILUO tag: '{tag}'.")
-    E069 = ("Invalid gold-standard parse tree. Found cycle between word "
-            "IDs: {cycle} (tokens: {cycle_tokens}) in the document starting "
-            "with tokens: {doc_tokens}.")
-    E070 = ("Invalid gold-standard data. Number of documents ({n_docs}) "
-            "does not align with number of annotations ({n_annots}).")
     E071 = ("Error creating lexeme: specified orth ID ({orth}) does not "
             "match the one in the vocab ({vocab_orth}).")
-    E072 = ("Error serializing lexeme: expected data length {length}, "
-            "got {bad_length}.")
     E073 = ("Cannot assign vector of length {new_length}. Existing vectors "
             "are of length {length}. You can use `vocab.reset_vectors` to "
             "clear the existing vectors and resize the table.")
     E074 = ("Error interpreting compiled match pattern: patterns are expected "
             "to end with the attribute {attr}. Got: {bad_attr}.")
-    E075 = ("Error accepting match: length ({length}) > maximum length "
-            "({max_len}).")
-    E076 = ("Error setting tensor on Doc: tensor has {rows} rows, while Doc "
-            "has {words} words.")
-    E077 = ("Error computing {value}: number of Docs ({n_docs}) does not "
-            "equal number of GoldParse objects ({n_golds}) in batch.")
-    E078 = ("Error computing score: number of words in Doc ({words_doc}) does "
-            "not equal number of words in GoldParse ({words_gold}).")
-    E079 = ("Error computing states in beam: number of predicted beams "
-            "({pbeams}) does not equal number of gold beams ({gbeams}).")
-    E080 = ("Duplicate state found in beam: {key}.")
-    E081 = ("Error getting gradient in beam: number of histories ({n_hist}) "
-            "does not equal number of losses ({losses}).")
     E082 = ("Error deprojectivizing parse: number of heads ({n_heads}), "
             "projective heads ({n_proj_heads}) and labels ({n_labels}) do not "
             "match.")
@@ -345,8 +303,6 @@ class Errors(object):
             "`getter` (plus optional `setter`) is allowed. Got: {nr_defined}")
     E084 = ("Error assigning label ID {label} to span: not in StringStore.")
     E085 = ("Can't create lexeme for string '{string}'.")
-    E086 = ("Error deserializing lexeme '{string}': orth ID {orth_id} does "
-            "not match hash {hash_id} in StringStore.")
     E087 = ("Unknown displaCy style: {style}.")
     E088 = ("Text of length {length} exceeds maximum of {max_length}. The "
             "v2.x parser and NER models require roughly 1GB of temporary "
@@ -388,7 +344,6 @@ class Errors(object):
     E103 = ("Trying to set conflicting doc.ents: '{span1}' and '{span2}'. A "
             "token can only be part of one entity, so make sure the entities "
             "you're setting don't overlap.")
-    E104 = ("Can't find JSON schema for '{name}'.")
     E105 = ("The Doc.print_tree() method is now deprecated. Please use "
             "Doc.to_json() instead or write your own function.")
     E106 = ("Can't find doc._.{attr} attribute specified in the underscore "
@@ -411,8 +366,6 @@ class Errors(object):
             "practically no advantage over pickling the parent Doc directly. "
             "So instead of pickling the span, pickle the Doc it belongs to or "
             "use Span.as_doc to convert the span to a standalone Doc object.")
-    E113 = ("The newly split token can only have one root (head = 0).")
-    E114 = ("The newly split token needs to have a root (head = 0).")
     E115 = ("All subtokens must have associated heads.")
     E116 = ("Cannot currently add labels to pretrained text classifier. Add "
             "labels before training begins. This functionality was available "
@@ -435,12 +388,9 @@ class Errors(object):
             "equal to span length ({span_len}).")
     E122 = ("Cannot find token to be split. Did it get merged?")
     E123 = ("Cannot find head of token to be split. Did it get merged?")
-    E124 = ("Cannot read from file: {path}. Supported formats: {formats}")
     E125 = ("Unexpected value: {value}")
     E126 = ("Unexpected matcher predicate: '{bad}'. Expected one of: {good}. "
             "This is likely a bug in spaCy, so feel free to open an issue.")
-    E127 = ("Cannot create phrase pattern representation for length 0. This "
-            "is likely a bug in spaCy.")
     E128 = ("Unsupported serialization argument: '{arg}'. The use of keyword "
             "arguments to exclude fields from being serialized or deserialized "
             "is now deprecated. Please use the `exclude` argument instead. "
@@ -482,8 +432,6 @@ class Errors(object):
             "provided {found}.")
     E143 = ("Labels for component '{name}' not initialized. Did you forget to "
             "call add_label()?")
-    E144 = ("Could not find parameter `{param}` when building the entity "
-            "linker model.")
     E145 = ("Error reading `{param}` from input file.")
     E146 = ("Could not access `{path}`.")
     E147 = ("Unexpected error in the {method} functionality of the "
@@ -495,8 +443,6 @@ class Errors(object):
             "the component matches the model being loaded.")
     E150 = ("The language of the `nlp` object and the `vocab` should be the "
             "same, but found '{nlp}' and '{vocab}' respectively.")
-    E151 = ("Trying to call nlp.update without required annotation types. "
-            "Expected top-level keys: {exp}. Got: {unexp}.")
     E152 = ("The attribute {attr} is not supported for token patterns. "
             "Please use the option validate=True with Matcher, PhraseMatcher, "
             "or EntityRuler for more details.")
@@ -533,11 +479,6 @@ class Errors(object):
             "that case.")
     E166 = ("Can only merge DocBins with the same pre-defined attributes.\n"
             "Current DocBin: {current}\nOther DocBin: {other}")
-    E167 = ("Unknown morphological feature: '{feat}' ({feat_id}). This can "
-            "happen if the tagger was trained with a different set of "
-            "morphological features. If you're using a pretrained model, make "
-            "sure that your models are up to date:\npython -m spacy validate")
-    E168 = ("Unknown field: {field}")
     E169 = ("Can't find module: {module}")
     E170 = ("Cannot apply transition {name}: invalid for the current state.")
     E171 = ("Matcher.add received invalid on_match callback argument: expected "
@@ -548,8 +489,6 @@ class Errors(object):
     E173 = ("As of v2.2, the Lemmatizer is initialized with an instance of "
             "Lookups containing the lemmatization tables. See the docs for "
             "details: https://spacy.io/api/lemmatizer#init")
-    E174 = ("Architecture '{name}' not found in registry. Available "
-            "names: {names}")
     E175 = ("Can't remove rule for unknown match pattern ID: {key}")
     E176 = ("Alias '{alias}' is not defined in the Knowledge Base.")
     E177 = ("Ill-formed IOB input detected: {tag}")
@@ -597,10 +536,19 @@ class Errors(object):
     E198 = ("Unable to return {n} most similar vectors for the current vectors "
             "table, which contains {n_rows} vectors.")
     E199 = ("Unable to merge 0-length span at doc[{start}:{end}].")
-    E200 = ("Specifying a base model with a pretrained component '{component}' "
-            "can not be combined with adding a pretrained Tok2Vec layer.")
 
     # TODO: fix numbering after merging develop into master
+    E971 = ("Found incompatible lengths in Doc.from_array: {array_length} for the "
+            "array and {doc_length} for the Doc itself.")
+    E972 = ("Example.__init__ got None for '{arg}'. Requires Doc.")
+    E973 = ("Unexpected type for NER data")
+    E974 = ("Unknown {obj} attribute: {key}")
+    E975 = ("The method Example.from_dict expects a Doc as first argument, "
+            "but got {type}")
+    E976 = ("The method Example.from_dict expects a dict as second argument, "
+            "but received None.")
+    E977 = ("Can not compare a MorphAnalysis with a string object. "
+            "This is likely a bug in spaCy, so feel free to open an issue.")
     E978 = ("The {method} method of component {name} takes a list of Example objects, "
             "but found {types} instead.")
     E979 = ("Cannot convert {type} to an Example object.")
@@ -648,13 +596,8 @@ class Errors(object):
 @add_codes
 class TempErrors(object):
     T003 = ("Resizing pretrained Tagger models is not currently supported.")
-    T004 = ("Currently parser depth is hard-coded to 1. Received: {value}.")
     T007 = ("Can't yet set {attr} from Span. Vote for this feature on the "
             "issue tracker: http://github.com/explosion/spaCy/issues")
-    T008 = ("Bad configuration of Tagger. This is probably a bug within "
-            "spaCy. We changed the name of an internal attribute for loading "
-            "pretrained vectors, and the class has been passed the old name "
-            "(pretrained_dims) but not the new name (pretrained_vectors).")
 
 
 # fmt: on

spacy/gold/corpus.py

@@ -45,7 +45,7 @@ class Corpus:
 
     def make_examples(self, nlp, reference_docs, max_length=0):
         for reference in reference_docs:
-            if max_length >= 1 and len(reference) >= max_length:
+            if len(reference) >= max_length >= 1:
                 if reference.is_sentenced:
                     for ref_sent in reference.sents:
                         yield Example(

spacy/gold/example.pyx

@@ -2,7 +2,6 @@ import warnings
 
 import numpy
 
-from ..tokens import Token
 from ..tokens.doc cimport Doc
 from ..tokens.span cimport Span
 from ..tokens.span import Span
@@ -11,9 +10,8 @@ from .align cimport Alignment
 from .iob_utils import biluo_to_iob, biluo_tags_from_offsets, biluo_tags_from_doc
 from .iob_utils import spans_from_biluo_tags
 from .align import Alignment
-from ..errors import Errors, AlignmentError
+from ..errors import Errors, Warnings
 from ..syntax import nonproj
-from ..util import get_words_and_spaces
 
 
 cpdef Doc annotations2doc(vocab, tok_annot, doc_annot):
@@ -32,11 +30,10 @@ cpdef Doc annotations2doc(vocab, tok_annot, doc_annot):
 cdef class Example:
     def __init__(self, Doc predicted, Doc reference, *, Alignment alignment=None):
         """ Doc can either be text, or an actual Doc """
-        msg = "Example.__init__ got None for '{arg}'. Requires Doc."
         if predicted is None:
-            raise TypeError(msg.format(arg="predicted"))
+            raise TypeError(Errors.E972.format(arg="predicted"))
         if reference is None:
-            raise TypeError(msg.format(arg="reference"))
+            raise TypeError(Errors.E972.format(arg="reference"))
         self.x = predicted
         self.y = reference
         self._alignment = alignment
@@ -47,7 +44,7 @@ cdef class Example:
 
         def __set__(self, doc):
             self.x = doc
-    
+
     property reference:
         def __get__(self):
             return self.y
@@ -60,13 +57,13 @@ cdef class Example:
             self.x.copy(),
             self.y.copy()
         )
- 
+
     @classmethod
     def from_dict(cls, Doc predicted, dict example_dict):
         if example_dict is None:
-            raise ValueError("Example.from_dict expected dict, received None")
+            raise ValueError(Errors.E976)
         if not isinstance(predicted, Doc):
-            raise TypeError(f"Argument 1 should be Doc. Got {type(predicted)}")
+            raise TypeError(Errors.E975.format(type=type(predicted)))
         example_dict = _fix_legacy_dict_data(example_dict)
         tok_dict, doc_dict = _parse_example_dict_data(example_dict)
         if "ORTH" not in tok_dict:
@@ -78,7 +75,7 @@ cdef class Example:
             predicted,
             annotations2doc(predicted.vocab, tok_dict, doc_dict)
         )
-    
+
     @property
     def alignment(self):
         if self._alignment is None:
@@ -118,7 +115,8 @@ cdef class Example:
         aligned_deps = [None] * self.x.length
         heads = [token.head.i for token in self.y]
         deps = [token.dep_ for token in self.y]
-        heads, deps = nonproj.projectivize(heads, deps)
+        if projectivize:
+            heads, deps = nonproj.projectivize(heads, deps)
         for cand_i in range(self.x.length):
             gold_i = cand_to_gold[cand_i]
             if gold_i is not None: # Alignment found
@@ -151,7 +149,7 @@ cdef class Example:
                     x_text = self.x.text[end_char:]
                     x_text_offset = end_char
         x_tags = biluo_tags_from_offsets(
-            self.x, 
+            self.x,
             [(e.start_char, e.end_char, e.label_) for e in x_spans],
             missing=None
         )
@@ -245,11 +243,11 @@ def _annot2array(vocab, tok_annot, doc_annot):
             elif key == "cats":
                 pass
             else:
-                raise ValueError(f"Unknown doc attribute: {key}")
+                raise ValueError(Errors.E974.format(obj="doc", key=key))
 
     for key, value in tok_annot.items():
         if key not in IDS:
-            raise ValueError(f"Unknown token attribute: {key}")
+            raise ValueError(Errors.E974.format(obj="token", key=key))
         elif key in ["ORTH", "SPACY"]:
             pass
         elif key == "HEAD":
@@ -289,7 +287,7 @@ def _add_entities_to_doc(doc, ner_data):
         doc.ents = ner_data
         doc.ents = [span for span in ner_data if span.label_]
     else:
-        raise ValueError("Unexpected type for NER data")
+        raise ValueError(Errors.E973)
 
 
 def _parse_example_dict_data(example_dict):
@@ -341,7 +339,7 @@ def _fix_legacy_dict_data(example_dict):
     if "HEAD" in token_dict and "SENT_START" in token_dict:
         # If heads are set, we don't also redundantly specify SENT_START.
         token_dict.pop("SENT_START")
-        warnings.warn("Ignoring annotations for sentence starts, as dependency heads are set")
+        warnings.warn(Warnings.W092)
     return {
         "token_annotation": token_dict,
         "doc_annotation": doc_dict

spacy/gold/gold_io.pyx

@@ -145,7 +145,7 @@ def json_to_annotations(doc):
         example["doc_annotation"] = dict(
             cats=cats,
             entities=ner_tags,
-            links=paragraph.get("links", [])   # TODO: fix/test
+            links=paragraph.get("links", [])
         )
         yield example
 

spacy/morphology.pyx

@@ -107,9 +107,9 @@ cdef class Morphology:
         Returns the hash of the new analysis.
         """
         cdef MorphAnalysisC* tag_ptr
-        if features == self.EMPTY_MORPH:
-            features = ""
         if isinstance(features, str):
+            if features == self.EMPTY_MORPH:
+                features = ""
             tag_ptr = <MorphAnalysisC*>self.tags.get(<hash_t>self.strings[features])
             if tag_ptr != NULL:
                 return tag_ptr.key

spacy/pipeline/simple_ner.py

@@ -70,7 +70,7 @@ class SimpleNER(Pipe):
     def update(self, examples, set_annotations=False, drop=0.0, sgd=None, losses=None):
         if not any(_has_ner(eg) for eg in examples):
             return 0
-        docs = [eg.doc for eg in examples]
+        docs = [eg.predicted for eg in examples]
         set_dropout_rate(self.model, drop)
         scores, bp_scores = self.model.begin_update(docs)
         loss, d_scores = self.get_loss(examples, scores)
@@ -89,7 +89,8 @@ class SimpleNER(Pipe):
         d_scores = []
         truths = []
         for eg in examples:
-            gold_tags = [(tag if tag != "-" else None) for tag in eg.gold.ner]
+            tags = eg.get_aligned("TAG", as_string=True)
+            gold_tags = [(tag if tag != "-" else None) for tag in tags]
             if not self.is_biluo:
                 gold_tags = biluo_to_iob(gold_tags)
             truths.append(gold_tags)
@@ -128,8 +129,8 @@ class SimpleNER(Pipe):
         pass
 
 
-def _has_ner(eg):
+def _has_ner(example):
-    for ner_tag in eg.gold.ner:
+    for ner_tag in example.get_aligned_ner():
         if ner_tag != "-" and ner_tag is not None:
             return True
     else:

spacy/schemas.py

@@ -220,8 +220,11 @@ class TrainingSchema(BaseModel):
 
 
 class ProjectConfigAsset(BaseModel):
+    # fmt: off
     dest: StrictStr = Field(..., title="Destination of downloaded asset")
     url: StrictStr = Field(..., title="URL of asset")
+    checksum: str = Field(None, title="MD5 hash of file", regex=r"([a-fA-F\d]{32})")
+    # fmt: on
 
 
 class ProjectConfigCommand(BaseModel):
@@ -229,11 +232,15 @@ class ProjectConfigCommand(BaseModel):
     name: StrictStr = Field(..., title="Name of command")
     help: Optional[StrictStr] = Field(None, title="Command description")
     script: List[StrictStr] = Field([], title="List of CLI commands to run, in order")
-    dvc_deps: List[StrictStr] = Field([], title="Data Version Control dependencies")
+    deps: List[StrictStr] = Field([], title="Data Version Control dependencies")
-    dvc_outputs: List[StrictStr] = Field([], title="Data Version Control outputs")
+    outputs: List[StrictStr] = Field([], title="Data Version Control outputs")
-    dvc_outputs_no_cache: List[StrictStr] = Field([], title="Data Version Control outputs (no cache)")
+    outputs_no_cache: List[StrictStr] = Field([], title="Data Version Control outputs (no cache)")
     # fmt: on
 
+    class Config:
+        title = "A single named command specified in a project config"
+        extra = "forbid"
+
 
 class ProjectConfigSchema(BaseModel):
     # fmt: off

spacy/tests/test_gold.py

@@ -230,14 +230,13 @@ def test_json2docs_no_ner(en_vocab):
         Doc(
             doc.vocab,
             words=[w.text for w in doc],
-            spaces=[bool(w.whitespace_) for w in doc]
+            spaces=[bool(w.whitespace_) for w in doc],
         ),
-        doc
+        doc,
     )
     ner_tags = eg.get_aligned_ner()
     assert ner_tags == [None, None, None, None, None]
 
-         
 
 def test_split_sentences(en_vocab):
     words = ["I", "flew", "to", "San Francisco Valley", "had", "loads of fun"]
@@ -283,8 +282,8 @@ def test_split_sentences(en_vocab):
     assert split_examples[1].text == "had loads of fun "
 
 
-def test_gold_biluo_different_tokenization(en_vocab, en_tokenizer):
+@pytest.mark.xfail(reason="Alignment should be fixed after example refactor")
-    # one-to-many
+def test_gold_biluo_one_to_many(en_vocab, en_tokenizer):
     words = ["I", "flew to", "San Francisco Valley", "."]
     spaces = [True, True, False, False]
     doc = Doc(en_vocab, words=words, spaces=spaces)
@@ -292,9 +291,28 @@ def test_gold_biluo_different_tokenization(en_vocab, en_tokenizer):
     gold_words = ["I", "flew", "to", "San", "Francisco", "Valley", "."]
     example = Example.from_dict(doc, {"words": gold_words, "entities": entities})
     ner_tags = example.get_aligned_ner()
+    assert ner_tags == ["O", "O", "U-LOC", "O"]
+
+    entities = [
+        (len("I "), len("I flew to"), "ORG"),
+        (len("I flew to "), len("I flew to San Francisco Valley"), "LOC"),
+    ]
+    gold_words = ["I", "flew", "to", "San", "Francisco", "Valley", "."]
+    example = Example.from_dict(doc, {"words": gold_words, "entities": entities})
+    ner_tags = example.get_aligned_ner()
+    assert ner_tags == ["O", "U-ORG", "U-LOC", "O"]
+
+    entities = [
+        (len("I "), len("I flew"), "ORG"),
+        (len("I flew to "), len("I flew to San Francisco Valley"), "LOC"),
+    ]
+    gold_words = ["I", "flew", "to", "San", "Francisco", "Valley", "."]
+    example = Example.from_dict(doc, {"words": gold_words, "entities": entities})
+    ner_tags = example.get_aligned_ner()
     assert ner_tags == ["O", None, "U-LOC", "O"]
-    
+
-    # many-to-one
+
+def test_gold_biluo_many_to_one(en_vocab, en_tokenizer):
     words = ["I", "flew", "to", "San", "Francisco", "Valley", "."]
     spaces = [True, True, True, True, True, False, False]
     doc = Doc(en_vocab, words=words, spaces=spaces)
@@ -304,31 +322,38 @@ def test_gold_biluo_different_tokenization(en_vocab, en_tokenizer):
     ner_tags = example.get_aligned_ner()
     assert ner_tags == ["O", "O", "O", "B-LOC", "I-LOC", "L-LOC", "O"]
 
-    # misaligned
+    entities = [
+        (len("I "), len("I flew to"), "ORG"),
+        (len("I flew to "), len("I flew to San Francisco Valley"), "LOC"),
+    ]
+    gold_words = ["I", "flew to", "San Francisco Valley", "."]
+    example = Example.from_dict(doc, {"words": gold_words, "entities": entities})
+    ner_tags = example.get_aligned_ner()
+    assert ner_tags == ["O", "B-ORG", "L-ORG", "B-LOC", "I-LOC", "L-LOC", "O"]
+
+
+@pytest.mark.xfail(reason="Alignment should be fixed after example refactor")
+def test_gold_biluo_misaligned(en_vocab, en_tokenizer):
     words = ["I flew", "to", "San Francisco", "Valley", "."]
     spaces = [True, True, True, False, False]
     doc = Doc(en_vocab, words=words, spaces=spaces)
-    offset_start = len("I flew to ")
+    entities = [(len("I flew to "), len("I flew to San Francisco Valley"), "LOC")]
-    offset_end = len("I flew to San Francisco Valley")
-    entities = [(offset_start, offset_end, "LOC")]
-    links = {(offset_start, offset_end): {"Q816843": 1.0}}
     gold_words = ["I", "flew to", "San", "Francisco Valley", "."]
-    example = Example.from_dict(
+    example = Example.from_dict(doc, {"words": gold_words, "entities": entities})
-        doc, {"words": gold_words, "entities": entities, "links": links}
-    )
     ner_tags = example.get_aligned_ner()
-    assert ner_tags == [None, "O", "B-LOC", "L-LOC", "O"]
+    assert ner_tags == ["O", "O", "B-LOC", "L-LOC", "O"]
-    #assert example.get_aligned("ENT_KB_ID", as_string=True) == [
-    #    "",
-    #    "",
-    #    "Q816843",
-    #    "Q816843",
-    #    "",
-    #]
-    #assert example.to_dict()["doc_annotation"]["links"][(offset_start, offset_end)] == {
-    #    "Q816843": 1.0
-    #}
 
+    entities = [
+        (len("I "), len("I flew to"), "ORG"),
+        (len("I flew to "), len("I flew to San Francisco Valley"), "LOC"),
+    ]
+    gold_words = ["I", "flew to", "San", "Francisco Valley", "."]
+    example = Example.from_dict(doc, {"words": gold_words, "entities": entities})
+    ner_tags = example.get_aligned_ner()
+    assert ner_tags == [None, None, "B-LOC", "L-LOC", "O"]
+
+
+def test_gold_biluo_additional_whitespace(en_vocab, en_tokenizer):
     # additional whitespace tokens in GoldParse words
     words, spaces = get_words_and_spaces(
         ["I", "flew", "to", "San Francisco", "Valley", "."],
@@ -344,7 +369,8 @@ def test_gold_biluo_different_tokenization(en_vocab, en_tokenizer):
     ner_tags = example.get_aligned_ner()
     assert ner_tags == ["O", "O", "O", "O", "B-LOC", "L-LOC", "O"]
 
-    # from issue #4791
+
+def test_gold_biluo_4791(en_vocab, en_tokenizer):
     doc = en_tokenizer("I'll return the ₹54 amount")
     gold_words = ["I", "'ll", "return", "the", "₹", "54", "amount"]
     gold_spaces = [False, True, True, True, False, True, False]
@@ -593,7 +619,6 @@ def test_tuple_format_implicit_invalid():
         _train(train_data)
 
 
-
 def _train(train_data):
     nlp = English()
     ner = nlp.create_pipe("ner")

spacy/tests/util.py

@@ -1,15 +1,14 @@
 import numpy
 import tempfile
-import shutil
 import contextlib
 import srsly
-from pathlib import Path
 
 from spacy import Errors
 from spacy.tokens import Doc, Span
 from spacy.attrs import POS, TAG, HEAD, DEP, LEMMA, MORPH
 
 from spacy.vocab import Vocab
+from spacy.util import make_tempdir  # noqa: F401
 
 
 @contextlib.contextmanager
@@ -19,13 +18,6 @@ def make_tempfile(mode="r"):
     f.close()
 
 
-@contextlib.contextmanager
-def make_tempdir():
-    d = Path(tempfile.mkdtemp())
-    yield d
-    shutil.rmtree(str(d))
-
-
 def get_doc(
     vocab,
     words=[],

spacy/tokens/_serialize.py

@@ -9,7 +9,7 @@ from ..attrs import SPACY, ORTH, intify_attr
 from ..errors import Errors
 
 
-ALL_ATTRS = ("ORTH", "TAG", "HEAD", "DEP", "ENT_IOB", "ENT_TYPE", "LEMMA", "MORPH")
+ALL_ATTRS = ("ORTH", "TAG", "HEAD", "DEP", "ENT_IOB", "ENT_TYPE", "ENT_KB_ID", "LEMMA", "MORPH")
 
 
 class DocBin(object):

spacy/tokens/doc.pyx

@@ -816,7 +816,7 @@ cdef class Doc:
         cdef TokenC* tokens = self.c
         cdef int length = len(array)
         if length != len(self):
-            raise ValueError("Cannot set array values longer than the document.")
+            raise ValueError(Errors.E971.format(array_length=length, doc_length=len(self)))
 
         # Get set up for fast loading
         cdef Pool mem = Pool()

spacy/tokens/morphanalysis.pyx

@@ -1,6 +1,7 @@
 from libc.string cimport memset
 cimport numpy as np
 
+from ..errors import Errors
 from ..vocab cimport Vocab
 from ..typedefs cimport hash_t, attr_t
 from ..morphology cimport list_features, check_feature, get_by_field
@@ -49,6 +50,8 @@ cdef class MorphAnalysis:
         return self.key
 
     def __eq__(self, other):
+        if isinstance(other, str):
+            raise ValueError(Errors.E977)
         return self.key == other.key
 
     def __ne__(self, other):

spacy/util.py

@@ -19,6 +19,9 @@ from packaging.specifiers import SpecifierSet, InvalidSpecifier
 from packaging.version import Version, InvalidVersion
 import subprocess
 from contextlib import contextmanager
+import tempfile
+import shutil
+import hashlib
 
 
 try:
@@ -455,6 +458,37 @@ def working_dir(path: Union[str, Path]) -> None:
         os.chdir(prev_cwd)
 
 
+@contextmanager
+def make_tempdir():
+    """Execute a block in a temporary directory and remove the directory and
+    its contents at the end of the with block.
+
+    YIELDS (Path): The path of the temp directory.
+    """
+    d = Path(tempfile.mkdtemp())
+    yield d
+    shutil.rmtree(str(d))
+
+
+def get_hash(data) -> str:
+    """Get the hash for a JSON-serializable object.
+
+    data: The data to hash.
+    RETURNS (str): The hash.
+    """
+    data_str = srsly.json_dumps(data, sort_keys=True).encode("utf8")
+    return hashlib.md5(data_str).hexdigest()
+
+
+def get_checksum(path: Union[Path, str]) -> str:
+    """Get the checksum for a file given its file path.
+
+    path (Union[Path, str]): The file path.
+    RETURNS (str): The checksum.
+    """
+    return hashlib.md5(Path(path).read_bytes()).hexdigest()
+
+
 def is_in_jupyter():
     """Check if user is running spaCy from a Jupyter notebook by detecting the
     IPython kernel. Mainly used for the displaCy visualizer.