mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 01:16:28 +03:00
793430aa7a
* Integrate models into pipeline * Add basic serialization (maybe incorrect) * Fix pickle on vocab
77 lines
1.4 KiB
Cython
77 lines
1.4 KiB
Cython
from libc.stdint cimport uint8_t, uint32_t, int32_t, uint64_t
|
|
|
|
from .typedefs cimport flags_t, attr_t, hash_t
|
|
from .parts_of_speech cimport univ_pos_t
|
|
|
|
|
|
cdef struct LexemeC:
|
|
float* vector
|
|
|
|
flags_t flags
|
|
|
|
attr_t lang
|
|
|
|
attr_t id
|
|
attr_t length
|
|
|
|
attr_t orth
|
|
attr_t lower
|
|
attr_t norm
|
|
attr_t shape
|
|
attr_t prefix
|
|
attr_t suffix
|
|
|
|
attr_t cluster
|
|
|
|
float prob
|
|
float sentiment
|
|
float l2_norm
|
|
|
|
|
|
cdef struct SerializedLexemeC:
|
|
unsigned char[4*13 + 8] data
|
|
# sizeof(flags_t) # flags
|
|
# + sizeof(attr_t) # lang
|
|
# + sizeof(attr_t) # id
|
|
# + sizeof(attr_t) # length
|
|
# + sizeof(attr_t) # orth
|
|
# + sizeof(attr_t) # lower
|
|
# + sizeof(attr_t) # norm
|
|
# + sizeof(attr_t) # shape
|
|
# + sizeof(attr_t) # prefix
|
|
# + sizeof(attr_t) # suffix
|
|
# + sizeof(attr_t) # cluster
|
|
# + sizeof(float) # prob
|
|
# + sizeof(float) # cluster
|
|
# + sizeof(float) # l2_norm
|
|
|
|
|
|
cdef struct Entity:
|
|
hash_t id
|
|
int start
|
|
int end
|
|
int label
|
|
|
|
|
|
cdef struct TokenC:
|
|
const LexemeC* lex
|
|
uint64_t morph
|
|
univ_pos_t pos
|
|
bint spacy
|
|
int tag
|
|
int idx
|
|
int lemma
|
|
int sense
|
|
int head
|
|
int dep
|
|
bint sent_start
|
|
|
|
uint32_t l_kids
|
|
uint32_t r_kids
|
|
uint32_t l_edge
|
|
uint32_t r_edge
|
|
|
|
int ent_iob
|
|
int ent_type # TODO: Is there a better way to do this? Multiple sources of truth..
|
|
hash_t ent_id
|