mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
33 lines
660 B
Cython
33 lines
660 B
Cython
from libcpp.vector cimport vector
|
|
|
|
from preshed.maps cimport PreshMap
|
|
from cymem.cymem cimport Pool
|
|
from murmurhash.mrmr cimport hash64
|
|
|
|
from .structs cimport Lexeme, TokenC, UniStr
|
|
from .typedefs cimport utf8_t, id_t, hash_t
|
|
from .strings cimport StringStore
|
|
|
|
|
|
cdef union LexemesOrTokens:
|
|
const Lexeme* const* lexemes
|
|
TokenC* tokens
|
|
|
|
|
|
cdef struct _Cached:
|
|
LexemesOrTokens data
|
|
bint is_lex
|
|
int length
|
|
|
|
|
|
cdef class Vocab:
|
|
cpdef public get_lex_props
|
|
cdef Pool mem
|
|
cpdef readonly StringStore strings
|
|
cdef vector[Lexeme*] lexemes
|
|
|
|
cdef const Lexeme* get(self, Pool mem, UniStr* s) except NULL
|
|
|
|
cdef PreshMap _map
|
|
|