2014-12-19 22:51:33 +03:00
|
|
|
from libc.stdint cimport uint8_t, uint32_t
|
|
|
|
|
|
2015-01-25 08:31:07 +03:00
|
|
|
from .typedefs cimport flags_t, attr_t, id_t, hash_t
|
|
|
|
|
from .parts_of_speech cimport univ_pos_t
|
2014-12-19 22:51:33 +03:00
|
|
|
|
|
|
|
|
|
2015-01-12 02:26:22 +03:00
|
|
|
cdef struct LexemeC:
|
2015-01-21 18:04:24 +03:00
|
|
|
const float* repvec
|
2015-01-12 02:26:22 +03:00
|
|
|
|
2014-12-19 22:51:33 +03:00
|
|
|
flags_t flags
|
|
|
|
|
|
|
|
|
|
attr_t id
|
2015-01-12 03:23:44 +03:00
|
|
|
attr_t length
|
|
|
|
|
|
2015-01-22 18:08:25 +03:00
|
|
|
attr_t orth
|
2015-01-23 22:17:03 +03:00
|
|
|
attr_t lower
|
|
|
|
|
attr_t norm
|
2014-12-19 22:51:33 +03:00
|
|
|
attr_t shape
|
|
|
|
|
attr_t prefix
|
|
|
|
|
attr_t suffix
|
|
|
|
|
|
|
|
|
|
attr_t cluster
|
|
|
|
|
|
|
|
|
|
float prob
|
|
|
|
|
float sentiment
|
2015-02-07 16:43:17 +03:00
|
|
|
float l2_norm
|
2014-12-19 22:51:33 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef struct Morphology:
|
|
|
|
|
uint8_t number
|
|
|
|
|
uint8_t tenspect # Tense/aspect/voice
|
|
|
|
|
uint8_t mood
|
|
|
|
|
uint8_t gender
|
|
|
|
|
uint8_t person
|
|
|
|
|
uint8_t case
|
|
|
|
|
uint8_t misc
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef struct PosTag:
|
|
|
|
|
Morphology morph
|
|
|
|
|
int id
|
2015-01-25 08:31:07 +03:00
|
|
|
univ_pos_t pos
|
2014-12-19 22:51:33 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef struct TokenC:
|
2015-01-12 02:26:22 +03:00
|
|
|
const LexemeC* lex
|
2014-12-19 22:51:33 +03:00
|
|
|
Morphology morph
|
2015-01-25 08:31:07 +03:00
|
|
|
univ_pos_t pos
|
2015-01-17 08:21:17 +03:00
|
|
|
int tag
|
2014-12-19 22:51:33 +03:00
|
|
|
int idx
|
|
|
|
|
int lemma
|
|
|
|
|
int sense
|
|
|
|
|
int head
|
2015-01-17 08:21:17 +03:00
|
|
|
int dep
|
2015-01-31 05:44:16 +03:00
|
|
|
bint sent_end
|
2014-12-19 22:51:33 +03:00
|
|
|
uint32_t l_kids
|
|
|
|
|
uint32_t r_kids
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef struct Utf8Str:
|
|
|
|
|
id_t i
|
|
|
|
|
hash_t key
|
|
|
|
|
unsigned char* chars
|
|
|
|
|
int length
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef struct UniStr:
|
|
|
|
|
Py_UNICODE* chars
|
|
|
|
|
size_t n
|
|
|
|
|
hash_t key
|
