Fix remaining files. Reenable cython-lint check.

.github/workflows/tests.yml

@@ -48,7 +48,7 @@ jobs:
       - name: cython-lint
         run: |
           python -m pip install cython-lint -c requirements.txt
-          # cython-lint spacy --ignore E501,W291,E266
+          cython-lint spacy --ignore E501,W291,E266
 
   tests:
     name: Test

spacy/attrs.pxd

@@ -96,4 +96,4 @@ cdef enum attr_id_t:
     ENT_ID = symbols.ENT_ID
 
     IDX
-    SENT_END
+    SENT_END

spacy/morphology.pyx

@@ -83,10 +83,11 @@ cdef class Morphology:
         features = self.normalize_attrs(features)
         string_features = {self.strings.as_string(field): self.strings.as_string(values) for field, values in features.items()}
         # normalized UFEATS string with sorted fields and values
-        norm_feats_string = self.FEATURE_SEP.join(sorted([
-                self.FIELD_SEP.join([field, values])
-            for field, values in string_features.items()
-        ]))
+        norm_feats_string = self.FEATURE_SEP.join(
+            sorted(
+                [self.FIELD_SEP.join([field, values]) for field, values in string_features.items()]
+            )
+        )
         return norm_feats_string or self.EMPTY_MORPH
 
     def normalize_attrs(self, attrs):
@@ -192,6 +193,7 @@ cdef int get_n_by_field(attr_t* results, const MorphAnalysisC* morph, attr_t fie
             n_results += 1
     return n_results
 
+
 def unpickle_morphology(strings, tags):
     cdef Morphology morphology = Morphology(strings)
     for tag in tags:

spacy/strings.pyx

@@ -2,7 +2,6 @@
 cimport cython
 from libc.stdint cimport uint32_t
 from libc.string cimport memcpy
-from libcpp.set cimport set
 from murmurhash.mrmr cimport hash32, hash64
 
 import srsly
@@ -20,9 +19,10 @@ cdef inline bint _try_coerce_to_hash(object key, hash_t* out_hash):
     try:
         out_hash[0] = key
         return True
-    except:
+    except:  # no-cython-lint
         return False
 
+
 def get_string_id(key):
     """Get a string ID, handling the reserved symbols correctly. If the key is
     already an ID, return it.
@@ -87,7 +87,6 @@ cdef Utf8Str* _allocate(Pool mem, const unsigned char* chars, uint32_t length) e
     cdef int n_length_bytes
     cdef int i
     cdef Utf8Str* string = <Utf8Str*>mem.alloc(1, sizeof(Utf8Str))
-    cdef uint32_t ulength = length
     if length < sizeof(string.s):
         string.s[0] = <unsigned char>length
         memcpy(&string.s[1], chars, length)

spacy/structs.pxd

@@ -52,7 +52,7 @@ cdef struct TokenC:
 
     int sent_start
     int ent_iob
-    attr_t ent_type # TODO: Is there a better way to do this? Multiple sources of truth..
+    attr_t ent_type  # TODO: Is there a better way to do this? Multiple sources of truth..
     attr_t ent_kb_id
     hash_t ent_id
 

spacy/symbols.pyx

@@ -96,7 +96,7 @@ IDS = {
     "ADV": ADV,
     "AUX": AUX,
     "CONJ": CONJ,
-    "CCONJ": CCONJ, # U20
+    "CCONJ": CCONJ,  # U20
     "DET": DET,
     "INTJ": INTJ,
     "NOUN": NOUN,
@@ -421,7 +421,7 @@ IDS = {
     "ccomp": ccomp,
     "complm": complm,
     "conj": conj,
-    "cop": cop, # U20
+    "cop": cop,  # U20
     "csubj": csubj,
     "csubjpass": csubjpass,
     "dep": dep,
@@ -444,8 +444,8 @@ IDS = {
     "num": num,
     "number": number,
     "oprd": oprd,
-    "obj": obj, # U20
-    "obl": obl, # U20
+    "obj": obj,  # U20
+    "obl": obl,  # U20
     "parataxis": parataxis,
     "partmod": partmod,
     "pcomp": pcomp,