2015-07-13 20:58:26 +03:00
|
|
|
from cymem.cymem cimport Pool
|
|
|
|
|
cimport numpy as np
|
|
|
|
|
from preshed.counter cimport PreshCounter
|
|
|
|
|
|
|
|
|
|
from ..vocab cimport Vocab
|
|
|
|
|
from ..structs cimport TokenC, LexemeC
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ctypedef const LexemeC* const_Lexeme_ptr
|
|
|
|
|
ctypedef TokenC* TokenC_ptr
|
|
|
|
|
|
|
|
|
|
ctypedef fused LexemeOrToken:
|
|
|
|
|
const_Lexeme_ptr
|
|
|
|
|
TokenC_ptr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef class Doc:
|
2015-07-28 21:46:59 +03:00
|
|
|
cdef readonly Pool mem
|
|
|
|
|
cdef readonly Vocab vocab
|
2015-07-13 20:58:26 +03:00
|
|
|
|
|
|
|
|
cdef TokenC* data
|
|
|
|
|
|
|
|
|
|
cdef public bint is_tagged
|
|
|
|
|
cdef public bint is_parsed
|
|
|
|
|
|
2015-07-13 23:28:10 +03:00
|
|
|
cdef public list _py_tokens
|
|
|
|
|
|
2015-07-13 20:58:26 +03:00
|
|
|
cdef int length
|
|
|
|
|
cdef int max_length
|
|
|
|
|
|
2015-07-13 22:46:02 +03:00
|
|
|
cdef int push_back(self, LexemeOrToken lex_or_tok, bint trailing_space) except -1
|
2015-07-13 20:58:26 +03:00
|
|
|
|
|
|
|
|
cpdef np.ndarray to_array(self, object features)
|
|
|
|
|
|
|
|
|
|
cdef int set_parse(self, const TokenC* parsed) except -1
|
