mirror of
https://github.com/explosion/spaCy.git
synced 2025-08-05 21:00:19 +03:00
Make kb_id and following kw-only
This commit is contained in:
parent
5bbf8eb40f
commit
4a47e25a4a
|
@ -105,6 +105,7 @@ class Doc:
|
|||
start_idx: int,
|
||||
end_idx: int,
|
||||
label: Union[int, str] = ...,
|
||||
*,
|
||||
kb_id: Union[int, str] = ...,
|
||||
vector: Optional[Floats1d] = ...,
|
||||
alignment_mode: str = ...,
|
||||
|
|
|
@ -520,7 +520,7 @@ cdef class Doc:
|
|||
def doc(self):
|
||||
return self
|
||||
|
||||
def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, alignment_mode="strict", span_id=0):
|
||||
def char_span(self, int start_idx, int end_idx, label=0, *, kb_id=0, vector=None, alignment_mode="strict", span_id=0):
|
||||
"""Create a `Span` object from the slice
|
||||
`doc.text[start_idx : end_idx]`. Returns None if no valid `Span` can be
|
||||
created.
|
||||
|
@ -1605,7 +1605,7 @@ cdef class Doc:
|
|||
for span_group in doc_json.get("spans", {}):
|
||||
spans = []
|
||||
for span in doc_json["spans"][span_group]:
|
||||
char_span = self.char_span(span["start"], span["end"], span["label"], span["kb_id"])
|
||||
char_span = self.char_span(span["start"], span["end"], span["label"], kb_id=span["kb_id"])
|
||||
if char_span is None:
|
||||
raise ValueError(Errors.E1039.format(obj="span", start=span["start"], end=span["end"]))
|
||||
spans.append(char_span)
|
||||
|
|
|
@ -93,8 +93,8 @@ class Span:
|
|||
self,
|
||||
start_idx: int,
|
||||
end_idx: int,
|
||||
*,
|
||||
label: Union[int, str] = ...,
|
||||
*,
|
||||
kb_id: Union[int, str] = ...,
|
||||
vector: Optional[Floats1d] = ...,
|
||||
alignment_mode: str = ...,
|
||||
|
|
|
@ -666,7 +666,7 @@ cdef class Span:
|
|||
else:
|
||||
return self.doc[root]
|
||||
|
||||
def char_span(self, int start_idx, int end_idx, *, label=0, kb_id=0, vector=None, alignment_mode="strict", span_id=0):
|
||||
def char_span(self, int start_idx, int end_idx, label=0, *, kb_id=0, vector=None, alignment_mode="strict", span_id=0):
|
||||
"""Create a `Span` object from the slice `span.text[start : end]`.
|
||||
|
||||
start_idx (int): The index of the first character of the span.
|
||||
|
|
|
@ -214,6 +214,7 @@ alignment mode `"strict".
|
|||
| `start` | The index of the first character of the span. ~~int~~ |
|
||||
| `end` | The index of the last character after the span. ~~int~~ |
|
||||
| `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ |
|
||||
| _keyword-only_ | |
|
||||
| `kb_id` | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ |
|
||||
| `vector` | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~ |
|
||||
| `alignment_mode` | How character indices snap to token boundaries. Options: `"strict"` (no snapping), `"contract"` (span of all tokens completely within the character span), `"expand"` (span of all tokens at least partially covered by the character span). Defaults to `"strict"`. ~~str~~ |
|
||||
|
|
|
@ -190,8 +190,8 @@ the character indices don't map to a valid span.
|
|||
| ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `start_idx` | The index of the first character of the span. ~~int~~ |
|
||||
| `end_idx` | The index of the last character after the span. ~~int~~ |
|
||||
| _keyword-only_ | |
|
||||
| `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ |
|
||||
| _keyword-only_ | |
|
||||
| `kb_id` | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ |
|
||||
| `vector` | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~ |
|
||||
| `alignment_mode` <Tag variant="new">3.5.1</Tag> | How character indices snap to token boundaries. Options: `"strict"` (no snapping), `"contract"` (span of all tokens completely within the character span), `"expand"` (span of all tokens at least partially covered by the character span). Defaults to `"strict"`. ~~str~~ |
|
||||
|
|
Loading…
Reference in New Issue
Block a user