mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
1a5be63715
* cleanup Tokenizer fields * remove unused object from vocab * remove IS_OOV_DEPRECATED * add back in as FLAG13 * FLAG 18 instead * import fix * fix clumpsy fingers * revert symbol changes in favor of #11352 * bint instead of bool
47 lines
1.3 KiB
Cython
47 lines
1.3 KiB
Cython
from libcpp.vector cimport vector
|
|
from preshed.maps cimport PreshMap
|
|
from cymem.cymem cimport Pool
|
|
from murmurhash.mrmr cimport hash64
|
|
|
|
from .structs cimport LexemeC, TokenC
|
|
from .typedefs cimport attr_t, hash_t
|
|
from .strings cimport StringStore
|
|
from .morphology cimport Morphology
|
|
|
|
|
|
cdef LexemeC EMPTY_LEXEME
|
|
|
|
|
|
cdef union LexemesOrTokens:
|
|
const LexemeC* const* lexemes
|
|
const TokenC* tokens
|
|
|
|
|
|
cdef struct _Cached:
|
|
LexemesOrTokens data
|
|
bint is_lex
|
|
int length
|
|
|
|
|
|
cdef class Vocab:
|
|
cdef Pool mem
|
|
cdef readonly StringStore strings
|
|
cdef public Morphology morphology
|
|
cdef public object _vectors
|
|
cdef public object _lookups
|
|
cdef public object writing_system
|
|
cdef public object get_noun_chunks
|
|
cdef readonly int length
|
|
cdef public object lex_attr_getters
|
|
cdef public object cfg
|
|
|
|
cdef const LexemeC* get(self, Pool mem, str string) except NULL
|
|
cdef const LexemeC* get_by_orth(self, Pool mem, attr_t orth) except NULL
|
|
cdef const TokenC* make_fused_token(self, substrings) except NULL
|
|
|
|
cdef const LexemeC* _new_lexeme(self, Pool mem, str string) except NULL
|
|
cdef int _add_lex_to_vocab(self, hash_t key, const LexemeC* lex) except -1
|
|
cdef const LexemeC* _new_lexeme(self, Pool mem, str string) except NULL
|
|
|
|
cdef PreshMap _by_orth
|