Use minor version for compatibility check (#8403)

* Use minor version for compatibility check

* Use minor version of compatibility table
* Soften warning message about incompatible models
* Add test for presence of current version in compatibility table

* Add test for download compatibility table

* Use minor version of lower pin in error message if possible

* Fall back to spacy_git_version if available

* Fix unknown version string

spacy/cli/download.py

@@ -6,7 +6,7 @@ import typer
 
 from ._util import app, Arg, Opt, WHEEL_SUFFIX, SDIST_SUFFIX
 from .. import about
-from ..util import is_package, get_base_version, run_command
+from ..util import is_package, get_minor_version, run_command
 from ..errors import OLD_MODEL_SHORTCUTS
 
 
@@ -74,7 +74,7 @@ def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -
 
 
 def get_compatibility() -> dict:
-    version = get_base_version(about.__version__)
+    version = get_minor_version(about.__version__)
     r = requests.get(about.__compatibility__)
     if r.status_code != 200:
         msg.fail(

spacy/cli/validate.py

@@ -3,10 +3,12 @@ from pathlib import Path
 import sys
 import requests
 from wasabi import msg, Printer
+import warnings
 
+from ..errors import Warnings
 from ._util import app
 from .. import about
-from ..util import get_package_version, get_installed_models, get_base_version
+from ..util import get_package_version, get_installed_models, get_minor_version
 from ..util import get_package_path, get_model_meta, is_compatible_version
 
 
@@ -24,7 +26,7 @@ def validate_cli():
 
 def validate() -> None:
     model_pkgs, compat = get_model_pkgs()
-    spacy_version = get_base_version(about.__version__)
+    spacy_version = get_minor_version(about.__version__)
     current_compat = compat.get(spacy_version, {})
     if not current_compat:
         msg.warn(f"No compatible packages found for v{spacy_version} of spaCy")
@@ -44,8 +46,8 @@ def validate() -> None:
                 comp = msg.text("", color="green", icon="good", no_print=True)
                 version = msg.text(data["version"], color="green", no_print=True)
             else:
-                version = msg.text(data["version"], color="red", no_print=True)
-                comp = f"--> {compat.get(data['name'], ['n/a'])[0]}"
+                version = msg.text(data["version"], color="yellow", no_print=True)
+                comp = f"--> {current_compat.get(data['name'], ['n/a'])[0]}"
             rows.append((data["name"], data["spacy"], version, comp))
         msg.table(rows, header=header)
     else:
@@ -78,6 +80,8 @@ def get_model_pkgs(silent: bool = False) -> Tuple[dict, dict]:
     msg.good("Loaded compatibility table")
     compat = r.json()["spacy"]
     all_models = set()
+    with warnings.catch_warnings():
+        warnings.filterwarnings("ignore", message="\\[W09[45]")
         installed_models = get_installed_models()
     for spacy_v, models in dict(compat).items():
         all_models.update(models.keys())
@@ -92,6 +96,8 @@ def get_model_pkgs(silent: bool = False) -> Tuple[dict, dict]:
             spacy_version = about.__version__
         else:
             model_path = get_package_path(package)
+            with warnings.catch_warnings():
+                warnings.filterwarnings("ignore", message="\\[W09[45]")
                 model_meta = get_model_meta(model_path)
             spacy_version = model_meta.get("spacy_version", "n/a")
             is_compat = is_compatible_version(about.__version__, spacy_version)

spacy/errors.py

@@ -150,12 +150,12 @@ class Warnings:
             "released, because the model may say it's compatible when it's "
             'not. Consider changing the "spacy_version" in your meta.json to a '
             "version range, with a lower and upper pin. For example: {example}")
-    W095 = ("Model '{model}' ({model_version}) requires spaCy {version} and is "
-            "incompatible with the current version ({current}). This may lead "
-            "to unexpected results or runtime errors. To resolve this, "
-            "download a newer compatible model or retrain your custom model "
-            "with the current spaCy version. For more details and available "
-            "updates, run: python -m spacy validate")
+    W095 = ("Model '{model}' ({model_version}) was trained with spaCy "
+            "{version} and may not be 100% compatible with the current version "
+            "({current}). If you see errors or degraded performance, download "
+            "a newer compatible model or retrain your custom model with the "
+            "current spaCy version. For more details and available updates, "
+            "run: python -m spacy validate")
     W096 = ("The method `nlp.disable_pipes` is now deprecated - use "
             "`nlp.select_pipes` instead.")
     W100 = ("Skipping unsupported morphological feature(s): '{feature}'. "

spacy/tests/test_cli.py

@@ -10,6 +10,10 @@ from spacy.cli.init_config import init_config, RECOMMENDATIONS
 from spacy.cli._util import validate_project_commands, parse_config_overrides
 from spacy.cli._util import load_project_config, substitute_project_variables
 from spacy.cli._util import string_to_list
+from spacy import about
+from spacy.util import get_minor_version
+from spacy.cli.validate import get_model_pkgs
+from spacy.cli.download import get_compatibility, get_version
 from thinc.api import ConfigValidationError, Config
 import srsly
 import os
@@ -308,7 +312,8 @@ def test_project_config_validation2(config, n_errors):
 
 
 @pytest.mark.parametrize(
-    "int_value", [10, pytest.param("10", marks=pytest.mark.xfail)],
+    "int_value",
+    [10, pytest.param("10", marks=pytest.mark.xfail)],
 )
 def test_project_config_interpolation(int_value):
     variables = {"a": int_value, "b": {"c": "foo", "d": True}}
@@ -331,7 +336,8 @@ def test_project_config_interpolation(int_value):
 
 
 @pytest.mark.parametrize(
-    "greeting", [342, "everyone", "tout le monde", pytest.param("42", marks=pytest.mark.xfail)],
+    "greeting",
+    [342, "everyone", "tout le monde", pytest.param("42", marks=pytest.mark.xfail)],
 )
 def test_project_config_interpolation_override(greeting):
     variables = {"a": "world"}
@@ -423,7 +429,13 @@ def test_parse_cli_overrides():
 @pytest.mark.parametrize("pretraining", [True, False])
 def test_init_config(lang, pipeline, optimize, pretraining):
     # TODO: add more tests and also check for GPU with transformers
-    config = init_config(lang=lang, pipeline=pipeline, optimize=optimize, pretraining=pretraining, gpu=False)
+    config = init_config(
+        lang=lang,
+        pipeline=pipeline,
+        optimize=optimize,
+        pretraining=pretraining,
+        gpu=False,
+    )
     assert isinstance(config, Config)
     if pretraining:
         config["paths"]["raw_text"] = "my_data.jsonl"
@@ -474,3 +486,18 @@ def test_string_to_list(value):
 def test_string_to_list_intify(value):
     assert string_to_list(value, intify=False) == ["1", "2", "3"]
     assert string_to_list(value, intify=True) == [1, 2, 3]
+
+
+def test_download_compatibility():
+    model_name = "en_core_web_sm"
+    compatibility = get_compatibility()
+    version = get_version(model_name, compatibility)
+    assert get_minor_version(about.__version__) == get_minor_version(version)
+
+
+def test_validate_compatibility_table():
+    model_pkgs, compat = get_model_pkgs()
+    spacy_version = get_minor_version(about.__version__)
+    current_compat = compat.get(spacy_version, {})
+    assert len(current_compat) > 0
+    assert "en_core_web_sm" in current_compat

spacy/util.py

@@ -648,6 +648,19 @@ def get_model_version_range(spacy_version: str) -> str:
     return f">={spacy_version},<{release[0]}.{release[1] + 1}.0"
 
 
+def get_model_lower_version(constraint: str) -> Optional[str]:
+    """From a version range like >=1.2.3,<1.3.0 return the lower pin.
+    """
+    try:
+        specset = SpecifierSet(constraint)
+        for spec in specset:
+            if spec.operator in (">=", "==", "~="):
+                return spec.version
+    except Exception:
+        pass
+    return None
+
+
 def get_base_version(version: str) -> str:
     """Generate the base version without any prerelease identifiers.
 
@@ -701,10 +714,18 @@ def load_meta(path: Union[str, Path]) -> Dict[str, Any]:
             raise ValueError(Errors.E054.format(setting=setting))
     if "spacy_version" in meta:
         if not is_compatible_version(about.__version__, meta["spacy_version"]):
+            lower_version = get_model_lower_version(meta["spacy_version"])
+            lower_version = get_minor_version(lower_version)
+            if lower_version is not None:
+                lower_version = "v" + lower_version
+            elif "spacy_git_version" in meta:
+                lower_version = "git commit " + meta["spacy_git_version"]
+            else:
+                lower_version = "version unknown"
             warn_msg = Warnings.W095.format(
                 model=f"{meta['lang']}_{meta['name']}",
                 model_version=meta["version"],
-                version=meta["spacy_version"],
+                version=lower_version,
                 current=about.__version__,
             )
             warnings.warn(warn_msg)