Remove old model shortcuts (#11916)

* Remove old model shortcuts

* Remove error, docs warnings about shortcuts

* Fix import in util

Accidentally deleted the whole import and not just the old part...

* Change universe example to v3 style

* Switch ubuntu-latest to ubuntu-20.04 in main tests (#11928)

* Switch ubuntu-latest to ubuntu-20.04 in main tests

* Only use 20.04 for 3.6

* Update some model loading in Universe

* Add v2 tag to neuralcoref

* Use the spacy-version feature instead of a v2 tag

Co-authored-by: svlandeg <svlandeg@github.com>

spacy/cli/download.py

@@ -8,7 +8,6 @@ from ._util import app, Arg, Opt, WHEEL_SUFFIX, SDIST_SUFFIX
 from .. import about
 from ..util import is_package, get_minor_version, run_command
 from ..util import is_prerelease_version
-from ..errors import OLD_MODEL_SHORTCUTS
 
 
 @app.command(
@@ -61,12 +60,6 @@ def download(
         version = components[-1]
     else:
         model_name = model
-        if model in OLD_MODEL_SHORTCUTS:
-            msg.warn(
-                f"As of spaCy v3.0, shortcuts like '{model}' are deprecated. Please "
-                f"use the full pipeline package name '{OLD_MODEL_SHORTCUTS[model]}' instead."
-            )
-            model_name = OLD_MODEL_SHORTCUTS[model]
         compatibility = get_compatibility()
         version = get_version(model_name, compatibility)
 

spacy/errors.py

@@ -720,13 +720,6 @@ class Errors(metaclass=ErrorsWithCodes):
             "method in component '{name}'. If you want to use this "
             "method, make sure it's overwritten on the subclass.")
     E940 = ("Found NaN values in scores.")
-    E941 = ("Can't find model '{name}'. It looks like you're trying to load a "
-            "model from a shortcut, which is obsolete as of spaCy v3.0. To "
-            "load the model, use its full name instead:\n\n"
-            "nlp = spacy.load(\"{full}\")\n\nFor more details on the available "
-            "models, see the models directory: https://spacy.io/models. If you "
-            "want to create a blank model, use spacy.blank: "
-            "nlp = spacy.blank(\"{name}\")")
     E942 = ("Executing `after_{name}` callback failed. Expected the function to "
             "return an initialized nlp object but got: {value}. Maybe "
             "you forgot to return the modified object in your function?")
@@ -955,15 +948,6 @@ class Errors(metaclass=ErrorsWithCodes):
              "but got '{received_type}'")
 
 
-# Deprecated model shortcuts, only used in errors and warnings
-OLD_MODEL_SHORTCUTS = {
-    "en": "en_core_web_sm", "de": "de_core_news_sm", "es": "es_core_news_sm",
-    "pt": "pt_core_news_sm", "fr": "fr_core_news_sm", "it": "it_core_news_sm",
-    "nl": "nl_core_news_sm", "el": "el_core_news_sm", "nb": "nb_core_news_sm",
-    "lt": "lt_core_news_sm", "xx": "xx_ent_wiki_sm"
-}
-
-
 # fmt: on
 
 

spacy/util.py

@@ -40,7 +40,7 @@ except ImportError:
 
 from .symbols import ORTH
 from .compat import cupy, CudaStream, is_windows, importlib_metadata
-from .errors import Errors, Warnings, OLD_MODEL_SHORTCUTS
+from .errors import Errors, Warnings
 from . import about
 
 if TYPE_CHECKING:
@@ -427,8 +427,6 @@ def load_model(
             return load_model_from_path(Path(name), **kwargs)  # type: ignore[arg-type]
     elif hasattr(name, "exists"):  # Path or Path-like to model data
         return load_model_from_path(name, **kwargs)  # type: ignore[arg-type]
-    if name in OLD_MODEL_SHORTCUTS:
-        raise IOError(Errors.E941.format(name=name, full=OLD_MODEL_SHORTCUTS[name]))  # type: ignore[index]
     raise IOError(Errors.E050.format(name=name))
 
 

website/UNIVERSE.md

@@ -51,7 +51,7 @@ markup is correct.
         "import spacy",
         "import package_name",
         "",
-        "nlp = spacy.load('en')",
+        "nlp = spacy.load('en_core_web_sm')",
         "nlp.add_pipe(package_name)"
     ],
     "code_language": "python",

website/docs/usage/models.md

@@ -342,22 +342,6 @@ The easiest way to download a trained pipeline is via spaCy's
 [`download`](/api/cli#download) command. It takes care of finding the
 best-matching package compatible with your spaCy installation.
 
-> #### Important note for v3.0
->
-> Note that as of spaCy v3.0, shortcut links like `en` that create (potentially
-> brittle) symlinks in your spaCy installation are **deprecated**. To download
-> and load an installed pipeline package, use its full name:
->
-> ```diff
-> - python -m spacy download en
-> + python -m spacy download en_core_web_sm
-> ```
->
-> ```diff
-> - nlp = spacy.load("en")
-> + nlp = spacy.load("en_core_web_sm")
-> ```
-
 ```cli
 # Download best-matching version of a package for your spaCy installation
 $ python -m spacy download en_core_web_sm
@@ -489,17 +473,6 @@ spacy.cli.download("en_core_web_sm")
 To load a pipeline package, use [`spacy.load`](/api/top-level#spacy.load) with
 the package name or a path to the data directory:
 
-> #### Important note for v3.0
->
-> Note that as of spaCy v3.0, shortcut links like `en` that create (potentially
-> brittle) symlinks in your spaCy installation are **deprecated**. To download
-> and load an installed pipeline package, use its full name:
->
-> ```diff
-> - python -m spacy download en
-> + python -m spacy download en_core_web_sm
-> ```
-
 ```python
 import spacy
 nlp = spacy.load("en_core_web_sm")           # load package "en_core_web_sm"

website/meta/universe.json

@@ -1021,7 +1021,8 @@
             "author_links": {
                 "github": "mholtzscher"
             },
-            "category": ["pipeline"]
+            "category": ["pipeline"],
+            "spacy_version": 2
         },
         {
             "id": "spacy-sentence-segmenter",
@@ -1045,7 +1046,7 @@
         {
             "id": "spacy_cld",
             "title": "spaCy-CLD",
-            "slogan": "Add language detection to your spaCy pipeline using CLD2",
+            "slogan": "Add language detection to your spaCy v2 pipeline using CLD2",
             "description": "spaCy-CLD operates on `Doc` and `Span` spaCy objects. When called on a `Doc` or `Span`, the object is given two attributes: `languages` (a list of up to 3 language codes) and `language_scores` (a dictionary mapping language codes to confidence scores between 0 and 1).\n\nspacy-cld is a little extension that wraps the [PYCLD2](https://github.com/aboSamoor/pycld2) Python library, which in turn wraps the [Compact Language Detector 2](https://github.com/CLD2Owners/cld2) C library originally built at Google for the Chromium project. CLD2 uses character n-grams as features and a Naive Bayes classifier to identify 80+ languages from Unicode text strings (or XML/HTML). It can detect up to 3 different languages in a given document, and reports a confidence score (reported in with each language.",
             "github": "nickdavidhaynes/spacy-cld",
             "pip": "spacy_cld",
@@ -1065,7 +1066,8 @@
             "author_links": {
                 "github": "nickdavidhaynes"
             },
-            "category": ["pipeline"]
+            "category": ["pipeline"],
+            "spacy_version": 2
         },
         {
             "id": "spacy-iwnlp",
@@ -1139,7 +1141,8 @@
                 "github": "sammous"
             },
             "category": ["pipeline"],
-            "tags": ["pos", "lemmatizer", "french"]
+            "tags": ["pos", "lemmatizer", "french"],
+            "spacy_version": 2
         },
         {
             "id": "lemmy",
@@ -1333,8 +1336,8 @@
         },
         {
             "id": "neuralcoref",
-            "slogan": "State-of-the-art coreference resolution based on neural nets and spaCy",
+            "slogan": "State-of-the-art coreference resolution based on neural nets and spaCy v2",
-            "description": "This coreference resolution module is based on the super fast [spaCy](https://spacy.io/) parser and uses the neural net scoring model described in [Deep Reinforcement Learning for Mention-Ranking Coreference Models](http://cs.stanford.edu/people/kevclark/resources/clark-manning-emnlp2016-deep.pdf) by Kevin Clark and Christopher D. Manning, EMNLP 2016. Since ✨Neuralcoref v2.0, you can train the coreference resolution system on your own dataset — e.g., another language than English! — **provided you have an annotated dataset**. Note that to use neuralcoref with spaCy > 2.1.0, you'll have to install neuralcoref from source.",
+            "description": "This coreference resolution module is based on the super fast spaCy parser and uses the neural net scoring model described in [Deep Reinforcement Learning for Mention-Ranking Coreference Models](http://cs.stanford.edu/people/kevclark/resources/clark-manning-emnlp2016-deep.pdf) by Kevin Clark and Christopher D. Manning, EMNLP 2016. Since ✨Neuralcoref v2.0, you can train the coreference resolution system on your own dataset — e.g., another language than English! — **provided you have an annotated dataset**. Note that to use neuralcoref with spaCy > 2.1.0, you'll have to install neuralcoref from source, and v3+ is not supported.",
             "github": "huggingface/neuralcoref",
             "thumb": "https://i.imgur.com/j6FO9O6.jpg",
             "code_example": [
@@ -1355,7 +1358,8 @@
                 "github": "huggingface"
             },
             "category": ["standalone", "conversational", "models"],
-            "tags": ["coref"]
+            "tags": ["coref"],
+            "spacy_version": 2
         },
         {
             "id": "neuralcoref-vizualizer",
@@ -1431,7 +1435,7 @@
                 "import spacy",
                 "import explacy",
                 "",
-                "nlp = spacy.load('en')",
+                "nlp = spacy.load('en_core_web_sm')",
                 "explacy.print_parse_info(nlp, 'The salad was surprisingly tasty.')"
             ],
             "author": "Tyler Neylon",