explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-13 09:33:18 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix remaining files. Reenable cython-lint check.

Browse Source
This commit is contained in:
Raphael Mitsch 2023-07-04 09:32:50 +02:00
parent 94110a1c6d
commit 56c1fd00eb
6 changed files with 15 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/tests.yml vendored
View File

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

10
spacy/morphology.pyx
View File

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

5
spacy/strings.pyx
View File

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