mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
42 lines
1.3 KiB
Cython
42 lines
1.3 KiB
Cython
# cython: embedsignature=True
|
|
from cpython.ref cimport Py_INCREF
|
|
from cymem.cymem cimport Pool
|
|
from murmurhash.mrmr cimport hash64
|
|
|
|
from libc.string cimport memset
|
|
|
|
from .orth cimport word_shape
|
|
from .typedefs cimport attr_t
|
|
import numpy
|
|
|
|
|
|
memset(&EMPTY_LEXEME, 0, sizeof(LexemeC))
|
|
|
|
|
|
cdef int set_lex_struct_props(LexemeC* lex, dict props, StringStore string_store,
|
|
const float* empty_vec) except -1:
|
|
lex.length = props['length']
|
|
lex.orth = string_store[props['orth']]
|
|
lex.lower = string_store[props['lower']]
|
|
lex.norm = string_store[props['norm']]
|
|
lex.shape = string_store[props['shape']]
|
|
lex.prefix = string_store[props['prefix']]
|
|
lex.suffix = string_store[props['suffix']]
|
|
|
|
lex.cluster = props['cluster']
|
|
lex.prob = props['prob']
|
|
lex.sentiment = props['sentiment']
|
|
|
|
lex.flags = props['flags']
|
|
lex.repvec = empty_vec
|
|
|
|
|
|
cdef class Lexeme:
|
|
"""An entry in the vocabulary. A Lexeme has no string context --- it's a
|
|
word-type, as opposed to a word token. It therefore has no part-of-speech
|
|
tag, dependency parse, or lemma (lemmatization depends on the part-of-speech
|
|
tag).
|
|
"""
|
|
def __cinit__(self, int vec_size):
|
|
self.repvec = numpy.ndarray(shape=(vec_size,), dtype=numpy.float32)
|