Partially work around pending deprecation of pkg_resources (#12368)

* Handle deprecation of pkg_resources

* Replace `pkg_resources` with `importlib_metadata` for `spacy info
--url`
* Remove requirements check from `spacy project` given the lack of
alternatives

* Fix installed model URL method and CI test

* Fix types/handling, simplify catch-all return

* Move imports instead of disabling requirements check

* Format

* Reenable test with ignored deprecation warning

* Fix except

* Fix return

.github/azure-steps.yml

@@ -59,6 +59,11 @@ steps:
     displayName: 'Test download CLI'
     condition: eq(variables['python_version'], '3.8')
 
+  - script: |
+      python -W error -m spacy info ca_core_news_sm | grep -q download_url
+    displayName: 'Test download_url in info CLI'
+    condition: eq(variables['python_version'], '3.8')
+
   - script: |
       python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
     displayName: 'Test no warnings on load (#11713)'

spacy/cli/info.py

@@ -1,6 +1,5 @@
 from typing import Optional, Dict, Any, Union, List
 import platform
-import pkg_resources
 import json
 from pathlib import Path
 from wasabi import Printer, MarkdownRenderer
@@ -10,6 +9,7 @@ from ._util import app, Arg, Opt, string_to_list
 from .download import get_model_filename, get_latest_version
 from .. import util
 from .. import about
+from ..compat import importlib_metadata
 
 
 @app.command("info")
@@ -137,15 +137,14 @@ def info_installed_model_url(model: str) -> Optional[str]:
     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
+        dist = importlib_metadata.distribution(model)
+        text = dist.read_text("direct_url.json")
+        if isinstance(text, str):
+            data = json.loads(text)
+            return data["url"]
     except Exception:
-        # something else, like no file or invalid JSON
-        return None
+        pass
+    return None
 
 
 def info_model_url(model: str) -> Dict[str, Any]:

spacy/cli/project/run.py

@@ -2,7 +2,6 @@ from typing import Optional, List, Dict, Sequence, Any, Iterable, Tuple
 import os.path
 from pathlib import Path
 
-import pkg_resources
 from wasabi import msg
 from wasabi.util import locale_escape
 import sys
@@ -331,6 +330,7 @@ def _check_requirements(requirements: List[str]) -> Tuple[bool, bool]:
     RETURNS (Tuple[bool, bool]): Whether (1) any packages couldn't be imported, (2) any packages with version conflicts
         exist.
     """
+    import pkg_resources
 
     failed_pkgs_msgs: List[str] = []
     conflicting_pkgs_msgs: List[str] = []

spacy/tests/test_cli.py

@@ -2,7 +2,6 @@ import os
 import math
 from collections import Counter
 from typing import Tuple, List, Dict, Any
-import pkg_resources
 import time
 from pathlib import Path
 
@@ -1126,6 +1125,7 @@ def test_cli_find_threshold(capsys):
                 )
 
 
+@pytest.mark.filterwarnings("ignore::DeprecationWarning")
 @pytest.mark.parametrize(
     "reqs,output",
     [
@@ -1158,6 +1158,8 @@ def test_cli_find_threshold(capsys):
     ],
 )
 def test_project_check_requirements(reqs, output):
+    import pkg_resources
+
     # excessive guard against unlikely package name
     try:
         pkg_resources.require("spacyunknowndoesnotexist12345")