Merge pull request #11448 from shadeMe/merge-develop-into-v4

Merge `develop` into `v4`

Author: shadeMe

pyproject.toml

@@ -6,7 +6,6 @@ requires = [
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
     "thinc>=8.1.0,<8.2.0",
-    "pathy",
     "numpy>=1.15.0",
 ]
 build-backend = "setuptools.build_meta"

requirements.txt

@@ -1,5 +1,5 @@
 # Our libraries
-spacy-legacy>=3.0.9,<3.1.0
+spacy-legacy>=3.0.10,<3.1.0
 spacy-loggers>=1.0.0,<2.0.0
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
@@ -34,4 +34,5 @@ mypy>=0.910,<0.970; platform_machine!='aarch64'
 types-dataclasses>=0.1.3; python_version < "3.7"
 types-mock>=0.1.1
 types-requests
+types-setuptools>=57.0.0
 black>=22.0,<23.0

setup.cfg

@@ -33,7 +33,7 @@ include_package_data = true
 python_requires = >=3.6
 install_requires =
     # Our libraries
-    spacy-legacy>=3.0.9,<3.1.0
+    spacy-legacy>=3.0.10,<3.1.0
     spacy-loggers>=1.0.0,<2.0.0
     murmurhash>=0.28.0,<1.1.0
     cymem>=2.0.2,<2.1.0
@@ -42,9 +42,9 @@ install_requires =
     wasabi>=0.9.1,<1.1.0
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
+    # Third-party dependencies
     typer>=0.3.0,<0.5.0
     pathy>=0.3.5
-    # Third-party dependencies
     tqdm>=4.38.0,<5.0.0
     numpy>=1.15.0
     requests>=2.13.0,<3.0.0

spacy/__init__.py

@@ -31,21 +31,21 @@ def load(
     name: Union[str, Path],
     *,
     vocab: Union[Vocab, bool] = True,
-    disable: Iterable[str] = util.SimpleFrozenList(),
-    enable: Iterable[str] = util.SimpleFrozenList(),
-    exclude: Iterable[str] = util.SimpleFrozenList(),
+    disable: Union[str, Iterable[str]] = util.SimpleFrozenList(),
+    enable: Union[str, Iterable[str]] = util.SimpleFrozenList(),
+    exclude: Union[str, Iterable[str]] = util.SimpleFrozenList(),
     config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(),
 ) -> Language:
     """Load a spaCy model from an installed package or a local path.
 
     name (str): Package name or model path.
     vocab (Vocab): A Vocab object. If True, a vocab is created.
-    disable (Iterable[str]): Names of pipeline components to disable. Disabled
+    disable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to disable. Disabled
         pipes will be loaded but they won't be run unless you explicitly
         enable them by calling nlp.enable_pipe.
-    enable (Iterable[str]): Names of pipeline components to enable. All other
+    enable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to enable. All other
         pipes will be disabled (but can be enabled later using nlp.enable_pipe).
-    exclude (Iterable[str]): Names of pipeline components to exclude. Excluded
+    exclude (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to exclude. Excluded
         components won't be loaded.
     config (Dict[str, Any] / Config): Config overrides as nested dict or dict
         keyed by section values in dot notation.

spacy/cli/download.py

@@ -20,7 +20,7 @@ def download_cli(
     ctx: typer.Context,
     model: str = Arg(..., help="Name of pipeline package to download"),
     direct: bool = Opt(False, "--direct", "-d", "-D", help="Force direct download of name + version"),
-    sdist: bool = Opt(False, "--sdist", "-S", help="Download sdist (.tar.gz) archive instead of pre-built binary wheel")
+    sdist: bool = Opt(False, "--sdist", "-S", help="Download sdist (.tar.gz) archive instead of pre-built binary wheel"),
     # fmt: on
 ):
     """
@@ -36,7 +36,12 @@ def download_cli(
     download(model, direct, sdist, *ctx.args)
 
 
-def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -> None:
+def download(
+    model: str,
+    direct: bool = False,
+    sdist: bool = False,
+    *pip_args,
+) -> None:
     if (
         not (is_package("spacy") or is_package("spacy-nightly"))
         and "--no-deps" not in pip_args
@@ -50,13 +55,10 @@ def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -
             "dependencies, you'll have to install them manually."
         )
         pip_args = pip_args + ("--no-deps",)
-    suffix = SDIST_SUFFIX if sdist else WHEEL_SUFFIX
-    dl_tpl = "{m}-{v}/{m}-{v}{s}#egg={m}=={v}"
     if direct:
         components = model.split("-")
         model_name = "".join(components[:-1])
         version = components[-1]
-        download_model(dl_tpl.format(m=model_name, v=version, s=suffix), pip_args)
     else:
         model_name = model
         if model in OLD_MODEL_SHORTCUTS:
@@ -67,13 +69,26 @@ def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -
             model_name = OLD_MODEL_SHORTCUTS[model]
         compatibility = get_compatibility()
         version = get_version(model_name, compatibility)
-        download_model(dl_tpl.format(m=model_name, v=version, s=suffix), pip_args)
+
+    filename = get_model_filename(model_name, version, sdist)
+
+    download_model(filename, pip_args)
     msg.good(
         "Download and installation successful",
         f"You can now load the package via spacy.load('{model_name}')",
     )
 
 
+def get_model_filename(model_name: str, version: str, sdist: bool = False) -> str:
+    dl_tpl = "{m}-{v}/{m}-{v}{s}"
+    egg_tpl = "#egg={m}=={v}"
+    suffix = SDIST_SUFFIX if sdist else WHEEL_SUFFIX
+    filename = dl_tpl.format(m=model_name, v=version, s=suffix)
+    if sdist:
+        filename += egg_tpl.format(m=model_name, v=version)
+    return filename
+
+
 def get_compatibility() -> dict:
     if is_prerelease_version(about.__version__):
         version: Optional[str] = about.__version__
@@ -105,6 +120,11 @@ def get_version(model: str, comp: dict) -> str:
     return comp[model][0]
 
 
+def get_latest_version(model: str) -> str:
+    comp = get_compatibility()
+    return get_version(model, comp)
+
+
 def download_model(
     filename: str, user_pip_args: Optional[Sequence[str]] = None
 ) -> None:

spacy/cli/info.py

@@ -1,10 +1,13 @@
 from typing import Optional, Dict, Any, Union, List
 import platform
+import pkg_resources
+import json
 from pathlib import Path
 from wasabi import Printer, MarkdownRenderer
 import srsly
 
 from ._util import app, Arg, Opt, string_to_list
+from .download import get_model_filename, get_latest_version
 from .. import util
 from .. import about
 
@@ -16,17 +19,27 @@ def info_cli(
     markdown: bool = Opt(False, "--markdown", "-md", help="Generate Markdown for GitHub issues"),
     silent: bool = Opt(False, "--silent", "-s", "-S", help="Don't print anything (just return)"),
     exclude: str = Opt("labels", "--exclude", "-e", help="Comma-separated keys to exclude from the print-out"),
+    url: bool = Opt(False, "--url", "-u", help="Print the URL to download the most recent compatible version of the pipeline"),
     # fmt: on
 ):
     """
     Print info about spaCy installation. If a pipeline is specified as an argument,
     print its meta information. Flag --markdown prints details in Markdown for easy
     copy-pasting to GitHub issues.
 
+    Flag --url prints only the download URL of the most recent compatible
+    version of the pipeline.
+
     DOCS: https://spacy.io/api/cli#info
     """
     exclude = string_to_list(exclude)
-    info(model, markdown=markdown, silent=silent, exclude=exclude)
+    info(
+        model,
+        markdown=markdown,
+        silent=silent,
+        exclude=exclude,
+        url=url,
+    )
 
 
 def info(
@@ -35,11 +48,20 @@ def info(
     markdown: bool = False,
     silent: bool = True,
     exclude: Optional[List[str]] = None,
+    url: bool = False,
 ) -> Union[str, dict]:
     msg = Printer(no_print=silent, pretty=not silent)
     if not exclude:
         exclude = []
-    if model:
+    if url:
+        if model is not None:
+            title = f"Download info for pipeline '{model}'"
+            data = info_model_url(model)
+            print(data["download_url"])
+            return data
+        else:
+            msg.fail("--url option requires a pipeline name", exits=1)
+    elif model:
         title = f"Info about pipeline '{model}'"
         data = info_model(model, silent=silent)
     else:
@@ -99,11 +121,43 @@ def info_model(model: str, *, silent: bool = True) -> Dict[str, Any]:
         meta["source"] = str(model_path.resolve())
     else:
         meta["source"] = str(model_path)
+    download_url = info_installed_model_url(model)
+    if download_url:
+        meta["download_url"] = download_url
     return {
         k: v for k, v in meta.items() if k not in ("accuracy", "performance", "speed")
     }
 
 
+def info_installed_model_url(model: str) -> Optional[str]:
+    """Given a pipeline name, get the download URL if available, otherwise
+    return None.
+
+    This is only available for pipelines installed as modules that have
+    dist-info available.
+    """
+    try:
+        dist = pkg_resources.get_distribution(model)
+        data = json.loads(dist.get_metadata("direct_url.json"))
+        return data["url"]
+    except pkg_resources.DistributionNotFound:
+        # no such package
+        return None
+    except Exception:
+        # something else, like no file or invalid JSON
+        return None
+
+def info_model_url(model: str) -> Dict[str, Any]:
+    """Return the download URL for the latest version of a pipeline."""
+    version = get_latest_version(model)
+
+    filename = get_model_filename(model, version)
+    download_url = about.__download_url__ + "/" + filename
+    release_tpl = "https://github.com/explosion/spacy-models/releases/tag/{m}-{v}"
+    release_url = release_tpl.format(m=model, v=version)
+    return {"download_url": download_url, "release_url": release_url}
+
+
 def get_markdown(
     data: Dict[str, Any],
     title: Optional[str] = None,

spacy/errors.py

@@ -230,8 +230,9 @@ class Errors(metaclass=ErrorsWithCodes):
             "initialized component.")
     E004 = ("Can't set up pipeline component: a factory for '{name}' already "
             "exists. Existing factory: {func}. New factory: {new_func}")
-    E005 = ("Pipeline component '{name}' returned None. If you're using a "
-            "custom component, maybe you forgot to return the processed Doc?")
+    E005 = ("Pipeline component '{name}' returned {returned_type} instead of a "
+            "Doc. If you're using a custom component, maybe you forgot to "
+            "return the processed Doc?")
     E006 = ("Invalid constraints for adding pipeline component. You can only "
             "set one of the following: before (component name or index), "
             "after (component name or index), first (True) or last (True). "

spacy/lang/ca/lemmatizer.py

@@ -72,10 +72,10 @@ def rule_lemmatize(self, token: Token) -> List[str]:
                         oov_forms.append(form)
         if not forms:
             forms.extend(oov_forms)
-        if not forms and string in lookup_table.keys():
-            forms.append(self.lookup_lemmatize(token)[0])
+
+        # use lookups, and fall back to the token itself
         if not forms:
-            forms.append(string)
+            forms.append(lookup_table.get(string, [string])[0])
         forms = list(dict.fromkeys(forms))
         self.cache[cache_key] = forms
         return forms

spacy/lang/fr/lemmatizer.py

@@ -53,11 +53,16 @@ def rule_lemmatize(self, token: Token) -> List[str]:
         rules = rules_table.get(univ_pos, [])
         string = string.lower()
         forms = []
+        # first try lookup in table based on upos
         if string in index:
             forms.append(string)
             self.cache[cache_key] = forms
             return forms
+
+        # then add anything in the exceptions table
         forms.extend(exceptions.get(string, []))
+
+        # if nothing found yet, use the rules
         oov_forms = []
         if not forms:
             for old, new in rules:
@@ -69,12 +74,14 @@ def rule_lemmatize(self, token: Token) -> List[str]:
                         forms.append(form)
                     else:
                         oov_forms.append(form)
+
+        # if still nothing, add the oov forms from rules
         if not forms:
             forms.extend(oov_forms)
-        if not forms and string in lookup_table.keys():
-            forms.append(self.lookup_lemmatize(token)[0])
+
+        # use lookups, which fall back to the token itself
         if not forms:
-            forms.append(string)
+            forms.append(lookup_table.get(string, [string])[0])
         forms = list(dict.fromkeys(forms))
         self.cache[cache_key] = forms
         return forms

spacy/lang/la/__init__.py

@@ -0,0 +1,18 @@
+from ...language import Language, BaseDefaults
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+from .stop_words import STOP_WORDS
+from .lex_attrs import LEX_ATTRS
+
+
+class LatinDefaults(BaseDefaults):
+    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    stop_words = STOP_WORDS
+    lex_attr_getters = LEX_ATTRS
+
+
+class Latin(Language):
+    lang = "la"
+    Defaults = LatinDefaults
+
+
+__all__ = ["Latin"]