mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
046c38bd26
A long time ago we went to some trouble to try to clean up "unused" strings, to avoid the `StringStore` growing in long-running processes. This never really worked reliably, and I think it was a really wrong approach. It's much better to let the user reload the `nlp` object as necessary, now that the string encoding is stable (in v1, the string IDs were sequential integers, making reloading the NLP object really annoying.) The extra book-keeping does make some performance difference, and the feature is unsed, so it's past time we killed it.
30 lines
711 B
Cython
30 lines
711 B
Cython
from libc.stdint cimport int64_t
|
|
from libcpp.vector cimport vector
|
|
from libcpp.set cimport set
|
|
from cymem.cymem cimport Pool
|
|
from preshed.maps cimport PreshMap
|
|
from murmurhash.mrmr cimport hash64
|
|
|
|
from .typedefs cimport attr_t, hash_t
|
|
|
|
|
|
cpdef hash_t hash_string(unicode string) except 0
|
|
cdef hash_t hash_utf8(char* utf8_string, int length) nogil
|
|
|
|
cdef unicode decode_Utf8Str(const Utf8Str* string)
|
|
|
|
|
|
ctypedef union Utf8Str:
|
|
unsigned char[8] s
|
|
unsigned char* p
|
|
|
|
|
|
cdef class StringStore:
|
|
cdef Pool mem
|
|
|
|
cdef vector[hash_t] keys
|
|
cdef public PreshMap _map
|
|
|
|
cdef const Utf8Str* intern_unicode(self, unicode py_string)
|
|
cdef const Utf8Str* _intern_utf8(self, char* utf8_string, int length)
|