https://github.com/explosion/cython-blis fails to build

.github/workflows/tests.yml

@@ -54,9 +54,9 @@ jobs:
 
   tests:
     name: Test
-    needs: Validate
+    needs: validate
     strategy:
-      fail-fast: true
+      fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
         python_version: ["3.9", "3.12", "3.13"]

spacy/cli/_util.py

@@ -99,7 +99,7 @@ def parse_config_overrides(
     RETURNS (Dict[str, Any]): The parsed dict, keyed by nested config setting.
     """
     env_string = os.environ.get(env_var, "") if env_var else ""
-    env_overrides = _parse_overrides(split_arg_string(env_string))
+    env_overrides = _parse_overrides(split_arg_string(env_string))  # type: ignore[operator]
     cli_overrides = _parse_overrides(args, is_cli=True)
     if cli_overrides:
         keys = [k for k in cli_overrides if k not in env_overrides]

spacy/lang/ht/__init__.py

@@ -5,11 +5,11 @@
 from ...language import BaseDefaults, Language
 from .lemmatizer import HaitianCreoleLemmatizer
 from .lex_attrs import LEX_ATTRS
-from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
 from .stop_words import STOP_WORDS
 from .syntax_iterators import SYNTAX_ITERATORS
-from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 from .tag_map import TAG_MAP
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 
 
 class HaitianCreoleDefaults(BaseDefaults):
@@ -22,10 +22,12 @@ class HaitianCreoleDefaults(BaseDefaults):
     stop_words = STOP_WORDS
     tag_map = TAG_MAP
 
+
 class HaitianCreole(Language):
     lang = "ht"
     Defaults = HaitianCreoleDefaults
 
+
 @HaitianCreole.factory(
     "lemmatizer",
     assigns=["token.lemma"],
@@ -49,4 +51,5 @@ def make_lemmatizer(
         nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
     )
 
+
 __all__ = ["HaitianCreole"]

spacy/lang/ht/lemmatizer.py

@@ -1,8 +1,8 @@
 from typing import List, Tuple
 
+from ...lookups import Lookups
 from ...pipeline import Lemmatizer
 from ...tokens import Token
-from ...lookups import Lookups
 
 
 class HaitianCreoleLemmatizer(Lemmatizer):

spacy/lang/ht/lex_attrs.py

@@ -49,6 +49,7 @@
     "P": "Pa",
 }
 
+
 def like_num(text):
     text = text.strip().lower()
     if text.startswith(("+", "-", "±", "~")):
@@ -69,9 +70,11 @@ def like_num(text):
         return True
     return False
 
+
 def norm_custom(text):
     return NORM_MAP.get(text, text.lower())
 
+
 LEX_ATTRS = {
     LIKE_NUM: like_num,
     NORM: norm_custom,

spacy/lang/ht/punctuation.py

@@ -4,10 +4,10 @@
     ALPHA_UPPER,
     CONCAT_QUOTES,
     HYPHENS,
-    LIST_PUNCT,
-    LIST_QUOTES,
     LIST_ELLIPSES,
     LIST_ICONS,
+    LIST_PUNCT,
+    LIST_QUOTES,
     merge_chars,
 )
 
@@ -16,28 +16,43 @@
 _prefixes_elision = "m n l y t k w"
 _prefixes_elision += " " + _prefixes_elision.upper()
 
-TOKENIZER_PREFIXES = LIST_PUNCT + LIST_QUOTES + [
-    r"(?:({pe})[{el}])(?=[{a}])".format(
-        a=ALPHA, el=ELISION, pe=merge_chars(_prefixes_elision)
-    )
-]
+TOKENIZER_PREFIXES = (
+    LIST_PUNCT
+    + LIST_QUOTES
+    + [
+        r"(?:({pe})[{el}])(?=[{a}])".format(
+            a=ALPHA, el=ELISION, pe=merge_chars(_prefixes_elision)
+        )
+    ]
+)
 
-TOKENIZER_SUFFIXES = LIST_PUNCT + LIST_QUOTES + LIST_ELLIPSES + [
-    r"(?<=[0-9])%",  # numbers like 10%
-    r"(?<=[0-9])(?:{h})".format(h=HYPHENS),  # hyphens after numbers
-    r"(?<=[{a}])['’]".format(a=ALPHA),  # apostrophes after letters
-    r"(?<=[{a}])['’][mwlnytk](?=\s|$)".format(a=ALPHA),  # contractions
-    r"(?<=[{a}0-9])\)",  # right parenthesis after letter/number
-    r"(?<=[{a}])\.(?=\s|$)".format(a=ALPHA),  # period after letter if space or end of string
-    r"(?<=\))[\.\?!]",  # punctuation immediately after right parenthesis
-]
+TOKENIZER_SUFFIXES = (
+    LIST_PUNCT
+    + LIST_QUOTES
+    + LIST_ELLIPSES
+    + [
+        r"(?<=[0-9])%",  # numbers like 10%
+        r"(?<=[0-9])(?:{h})".format(h=HYPHENS),  # hyphens after numbers
+        r"(?<=[{a}])['’]".format(a=ALPHA),  # apostrophes after letters
+        r"(?<=[{a}])['’][mwlnytk](?=\s|$)".format(a=ALPHA),  # contractions
+        r"(?<=[{a}0-9])\)",  # right parenthesis after letter/number
+        r"(?<=[{a}])\.(?=\s|$)".format(
+            a=ALPHA
+        ),  # period after letter if space or end of string
+        r"(?<=\))[\.\?!]",  # punctuation immediately after right parenthesis
+    ]
+)
 
-TOKENIZER_INFIXES = LIST_ELLIPSES + LIST_ICONS + [
-    r"(?<=[0-9])[+\-\*^](?=[0-9-])",
-    r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
-        al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
-    ),
-    r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
-    r"(?<=[{a}0-9])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
-    r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION),
-]
+TOKENIZER_INFIXES = (
+    LIST_ELLIPSES
+    + LIST_ICONS
+    + [
+        r"(?<=[0-9])[+\-\*^](?=[0-9-])",
+        r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
+            al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
+        ),
+        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}0-9])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
+        r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION),
+    ]
+)

spacy/lang/ht/stop_words.py

@@ -39,8 +39,7 @@
 
 men mèsi oswa osinon
 
-"""
-.split()
+""".split()
 )
 
 # Add common contractions, with and without apostrophe variants

spacy/lang/ht/tag_map.py

@@ -1,4 +1,22 @@
-from spacy.symbols import NOUN, VERB, AUX, ADJ, ADV, PRON, DET, ADP, SCONJ, CCONJ, PART, INTJ, NUM, PROPN, PUNCT, SYM, X
+from spacy.symbols import (
+    ADJ,
+    ADP,
+    ADV,
+    AUX,
+    CCONJ,
+    DET,
+    INTJ,
+    NOUN,
+    NUM,
+    PART,
+    PRON,
+    PROPN,
+    PUNCT,
+    SCONJ,
+    SYM,
+    VERB,
+    X,
+)
 
 TAG_MAP = {
     "NOUN": {"pos": NOUN},