2014-12-19 19:51:33 +00:00
|
|
|
from libc.stdint cimport uint8_t, uint32_t
|
|
|
|
|
|
2014-12-20 18:36:29 +00:00
|
|
|
from .typedefs cimport flags_t, attr_t, id_t, hash_t, univ_tag_t
|
2014-12-19 19:51:33 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef struct Lexeme:
|
|
|
|
|
flags_t flags
|
|
|
|
|
|
|
|
|
|
attr_t id
|
|
|
|
|
attr_t sic
|
|
|
|
|
attr_t dense
|
|
|
|
|
attr_t shape
|
|
|
|
|
attr_t prefix
|
|
|
|
|
attr_t suffix
|
|
|
|
|
|
|
|
|
|
attr_t length
|
|
|
|
|
attr_t cluster
|
|
|
|
|
attr_t pos_type
|
|
|
|
|
|
|
|
|
|
float prob
|
|
|
|
|
float sentiment
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
|
2014-12-20 18:36:29 +00:00
|
|
|
univ_tag_t pos
|
2014-12-19 19:51:33 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef struct TokenC:
|
|
|
|
|
const Lexeme* lex
|
|
|
|
|
Morphology morph
|
2014-12-24 06:42:00 +00:00
|
|
|
univ_tag_t pos
|
|
|
|
|
int fine_pos
|
2014-12-19 19:51:33 +00:00
|
|
|
int idx
|
|
|
|
|
int lemma
|
|
|
|
|
int sense
|
|
|
|
|
int head
|
|
|
|
|
int dep_tag
|
|
|
|
|
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
|
