mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 16:07:41 +03:00
b0228d8ea6
* chore: add cython-linter dev dependency * fix: lexeme.pyx * fix: morphology.pxd * fix: tokenizer.pxd * fix: vocab.pxd * fix: morphology.pxd (line length) * ci: add cython-lint * ci: fix cython-lint call * Fix kb/candidate.pyx. * Fix kb/kb.pyx. * Fix kb/kb_in_memory.pyx. * Fix kb. * Fix training/ partially. * Fix training/. Ignore trailing whitespaces and too long lines. * Fix ml/. * Fix matcher/. * Fix pipeline/. * Fix tokens/. * Fix build errors. Fix vocab.pyx. * Fix cython-lint install and run. * Fix lexeme.pyx, parts_of_speech.pxd, vectors.pyx. Temporarily disable cython-lint execution. * Fix attrs.pyx, lexeme.pyx, symbols.pxd, isort issues. * Make cython-lint install conditional. Fix tokenizer.pyx. * Fix remaining files. Reenable cython-lint check. * Readded parentheses. * Fix test_build_dependencies(). * Add explanatory comment to cython-lint execution. --------- Co-authored-by: Raphael Mitsch <r.mitsch@outlook.com>
71 lines
1.6 KiB
Cython
71 lines
1.6 KiB
Cython
cimport numpy as np
|
|
from cymem.cymem cimport Pool
|
|
|
|
from ..attrs cimport attr_id_t
|
|
from ..structs cimport LexemeC, SpanC, TokenC
|
|
from ..typedefs cimport attr_t
|
|
from ..vocab cimport Vocab
|
|
|
|
|
|
cdef attr_t get_token_attr(const TokenC* token, attr_id_t feat_name) nogil
|
|
cdef attr_t get_token_attr_for_matcher(const TokenC* token, attr_id_t feat_name) nogil
|
|
|
|
|
|
ctypedef const LexemeC* const_Lexeme_ptr
|
|
ctypedef const TokenC* const_TokenC_ptr
|
|
|
|
ctypedef fused LexemeOrToken:
|
|
const_Lexeme_ptr
|
|
const_TokenC_ptr
|
|
|
|
|
|
cdef int set_children_from_heads(TokenC* tokens, int start, int end) except -1
|
|
|
|
|
|
cdef int _set_lr_kids_and_edges(TokenC* tokens, int start, int end, int loop_count) except -1
|
|
|
|
|
|
cdef int token_by_start(const TokenC* tokens, int length, int start_char) except -2
|
|
|
|
|
|
cdef int token_by_end(const TokenC* tokens, int length, int end_char) except -2
|
|
|
|
|
|
cdef int [:, :] _get_lca_matrix(Doc, int start, int end)
|
|
|
|
|
|
cdef class Doc:
|
|
cdef readonly Pool mem
|
|
cdef readonly Vocab vocab
|
|
|
|
cdef public object _vector
|
|
cdef public object _vector_norm
|
|
|
|
cdef public object tensor
|
|
cdef public object cats
|
|
cdef public object user_data
|
|
cdef readonly object spans
|
|
|
|
cdef TokenC* c
|
|
|
|
cdef public float sentiment
|
|
|
|
cdef public dict user_hooks
|
|
cdef public dict user_token_hooks
|
|
cdef public dict user_span_hooks
|
|
|
|
cdef public bint has_unknown_spaces
|
|
|
|
cdef public object _context
|
|
|
|
cdef int length
|
|
cdef int max_length
|
|
|
|
cdef public object noun_chunks_iterator
|
|
|
|
cdef object __weakref__
|
|
|
|
cdef int push_back(self, LexemeOrToken lex_or_tok, bint has_space) except -1
|
|
|
|
cpdef np.ndarray to_array(self, object features)
|