mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
7e4cd7575c
* Refactor Docs.is_ flags
* Add derived `Doc.has_annotation` method
* `Doc.has_annotation(attr)` returns `True` for partial annotation
* `Doc.has_annotation(attr, require_complete=True)` returns `True` for
complete annotation
* Add deprecation warnings to `is_tagged`, `is_parsed`, `is_sentenced`
and `is_nered`
* Add `Doc._get_array_attrs()`, which returns a full list of `Doc` attrs
for use with `Doc.to_array`, `Doc.to_bytes` and `Doc.from_docs`. The
list is the `DocBin` attributes list plus `SPACY` and `LENGTH`.
Notes on `Doc.has_annotation`:
* `HEAD` is converted to `DEP` because heads don't have an unset state
* Accept `IS_SENT_START` as a synonym of `SENT_START`
Additional changes:
* Add `NORM`, `ENT_ID` and `SENT_START` to default attributes for
`DocBin`
* In `Doc.from_array()` the presence of `DEP` causes `HEAD` to override
`SENT_START`
* In `Doc.from_array()` using `attrs` other than
`Doc._get_array_attrs()` (i.e., a user's custom list rather than our
default internal list) with both `HEAD` and `SENT_START` shows a warning
that `HEAD` will override `SENT_START`
* `set_children_from_heads` does not require dependency labels to set
sentence boundaries and sets `sent_start` for all non-sentence starts to
`-1`
* Fix call to set_children_form_heads
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
70 lines
1.6 KiB
Cython
70 lines
1.6 KiB
Cython
from cymem.cymem cimport Pool
|
|
cimport numpy as np
|
|
|
|
from ..vocab cimport Vocab
|
|
from ..structs cimport TokenC, LexemeC
|
|
from ..typedefs cimport attr_t
|
|
from ..attrs cimport attr_id_t
|
|
|
|
|
|
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 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 list _py_tokens
|
|
|
|
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)
|