spaCy/spacy/vocab.pxd

40 lines
877 B
Cython
Raw Normal View History

from libcpp.vector cimport vector
from preshed.maps cimport PreshMap
from cymem.cymem cimport Pool
from murmurhash.mrmr cimport hash64
from .structs cimport LexemeC, TokenC, UniStr
from .typedefs cimport utf8_t, id_t, hash_t
from .strings cimport StringStore
cdef LexemeC EMPTY_LEXEME
2014-12-24 09:42:00 +03:00
cdef union LexemesOrTokens:
const LexemeC* const* lexemes
TokenC* tokens
cdef struct _Cached:
LexemesOrTokens data
bint is_lex
int length
cdef class Vocab:
cpdef public lexeme_props_getter
cdef Pool mem
cpdef readonly StringStore strings
cdef vector[const LexemeC*] lexemes
2015-07-08 13:36:38 +03:00
cdef readonly object pos_tags
cdef const LexemeC* get(self, Pool mem, UniStr* s) except NULL
cdef int _add_lex_to_vocab(self, hash_t key, const LexemeC* lex) except -1
2015-04-19 11:31:31 +03:00
cdef PreshMap _map
cdef readonly int repvec_length
cdef public object _codec