mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
61b04a70d5
* Add regression test * Run PhraseMatcher on Spans * Add test for PhraseMatcher on Spans and Docs * Add SCA * Add test with 3 matches in Doc, 1 match in Span * Update docs * Use doc.length for find_matches in tokenizer Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
22 lines
555 B
Cython
22 lines
555 B
Cython
from libcpp.vector cimport vector
|
|
from cymem.cymem cimport Pool
|
|
from preshed.maps cimport key_t, MapStruct
|
|
|
|
from ..attrs cimport attr_id_t
|
|
from ..structs cimport SpanC
|
|
from ..tokens.doc cimport Doc
|
|
from ..vocab cimport Vocab
|
|
|
|
|
|
cdef class PhraseMatcher:
|
|
cdef readonly Vocab vocab
|
|
cdef attr_id_t attr
|
|
cdef object _callbacks
|
|
cdef object _docs
|
|
cdef bint _validate
|
|
cdef MapStruct* c_map
|
|
cdef Pool mem
|
|
cdef key_t _terminal_hash
|
|
|
|
cdef void find_matches(self, Doc doc, int start_idx, int end_idx, vector[SpanC] *matches) nogil
|