explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-03 11:50:19 +03:00
Code Issues Packages Projects Releases Wiki Activity

Tidy up code

Browse Source
This commit is contained in:
richardpaulhudson 2022-11-03 21:26:47 +01:00
parent aaaed55459
commit 5d210a0f3b
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
spacy/strings.pyx
View File

@ -316,24 +316,24 @@ cdef class StringStore:
self.keys.push_back(key) self.keys.push_back(key)
return value return value
cdef const unsigned char* utf8_ptr(self, attr_t hash_val): @cython.boundscheck(False) # Deactivate bounds checking
cdef const unsigned char* utf8_ptr(self, const attr_t hash_val):
if hash_val == 0: if hash_val == 0:
return "".encode("utf-8") return b""
elif hash_val < len(SYMBOLS_BY_INT): elif hash_val < len(SYMBOLS_BY_INT):
return SYMBOLS_BY_INT[hash_val].encode("utf-8") return SYMBOLS_BY_INT[hash_val].encode("utf-8")
cdef Utf8Str* string = <Utf8Str*>self._map.get(hash_val) cdef Utf8Str* string = <Utf8Str*>self._map.get(hash_val)
cdef int i, length
if string.s[0] < sizeof(string.s) and string.s[0] != 0: if string.s[0] < sizeof(string.s) and string.s[0] != 0:
return string.s[1:string.s[0]+1] return string.s[1:string.s[0]+1]
elif string.p[0] < 255: elif string.p[0] < 255:
return string.p[1:string.p[0]+1] return string.p[1:string.p[0]+1]
else: cdef int i, length
i = 0 i = 0
length = 0 length = 0
while string.p[i] == 255: while string.p[i] == 255:
i += 1
length += 255
length += string.p[i]
i += 1 i += 1
return string.p[i:length + i] length += 255
length += string.p[i]
i += 1
return string.p[i:length + i]