explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add span_id to Span.char_span, update Doc/Span.char_span docs (#12196)

Browse Source 
* Add span_id to Span.char_span, update Doc/Span.char_span docs

`Span.char_span(id=)` should be removed in the future.

* Also use Union[int, str] in Doc docstring
This commit is contained in:
Adriane Boyd 2023-01-27 15:09:17 +01:00 committed by GitHub
parent 774c10fa39
commit 5f8a398bb9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 36 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/tests/doc/test_span.py
View File

@ -163,6 +163,18 @@ def test_char_span(doc, i_sent, i, j, text):
assert span.text == text assert span.text == text
def test_char_span_attributes(doc):
label = "LABEL"
kb_id = "KB_ID"
span_id = "SPAN_ID"
span1 = doc.char_span(20, 45, label=label, kb_id=kb_id, span_id=span_id)
span2 = doc[1:].char_span(15, 40, label=label, kb_id=kb_id, span_id=span_id)
assert span1.text == span2.text
assert span1.label_ == span2.label_ == label
assert span1.kb_id_ == span2.kb_id_ == kb_id
assert span1.id_ == span2.id_ == span_id
def test_spans_sent_spans(doc): def test_spans_sent_spans(doc):
sents = list(doc.sents) sents = list(doc.sents)
assert sents[0].start == 0 assert sents[0].start == 0

1
spacy/tokens/doc.pyi
View File

@ -108,6 +108,7 @@ class Doc:
kb_id: Union[int, str] = ..., kb_id: Union[int, str] = ...,
vector: Optional[Floats1d] = ..., vector: Optional[Floats1d] = ...,
alignment_mode: str = ..., alignment_mode: str = ...,
span_id: Union[int, str] = ...,
) -> Span: ... ) -> Span: ...
def similarity(self, other: Union[Doc, Span, Token, Lexeme]) -> float: ... def similarity(self, other: Union[Doc, Span, Token, Lexeme]) -> float: ...
@property @property

5
spacy/tokens/doc.pyx
View File

@ -528,9 +528,9 @@ cdef class Doc:
doc (Doc): The parent document. doc (Doc): The parent document.
start_idx (int): The index of the first character of the span. start_idx (int): The index of the first character of the span.
end_idx (int): The index of the first character after the span. end_idx (int): The index of the first character after the span.
label (uint64 or string): A label to attach to the Span, e.g. for label (Union[int, str]): A label to attach to the Span, e.g. for
named entities. named entities.
kb_id (uint64 or string): An ID from a KB to capture the meaning of a kb_id (Union[int, str]): An ID from a KB to capture the meaning of a
named entity. named entity.
vector (ndarray[ndim=1, dtype='float32']): A meaning representation of vector (ndarray[ndim=1, dtype='float32']): A meaning representation of
the span. the span.
@ -539,6 +539,7 @@ cdef class Doc:
with token boundaries), "contract" (span of all tokens completely with token boundaries), "contract" (span of all tokens completely
within the character span), "expand" (span of all tokens at least within the character span), "expand" (span of all tokens at least
partially covered by the character span). Defaults to "strict". partially covered by the character span). Defaults to "strict".
span_id (Union[int, str]): An identifier to associate with the span.
RETURNS (Span): The newly constructed object. RETURNS (Span): The newly constructed object.
DOCS: https://spacy.io/api/doc#char_span DOCS: https://spacy.io/api/doc#char_span

2
spacy/tokens/span.pyi
View File

@ -98,7 +98,9 @@ class Span:
label: Union[int, str] = ..., label: Union[int, str] = ...,
kb_id: Union[int, str] = ..., kb_id: Union[int, str] = ...,
vector: Optional[Floats1d] = ..., vector: Optional[Floats1d] = ...,
id: Union[int, str] = ...,
alignment_mode: str = ..., alignment_mode: str = ...,
span_id: Union[int, str] = ...,
) -> Span: ... ) -> Span: ...
@property @property
def conjuncts(self) -> Tuple[Token]: ... def conjuncts(self) -> Tuple[Token]: ...

10
spacy/tokens/span.pyx
View File

@ -639,26 +639,28 @@ cdef class Span:
else: else:
return self.doc[root] return self.doc[root]
def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, id=0, alignment_mode="strict"): def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, id=0, alignment_mode="strict", span_id=0):
"""Create a `Span` object from the slice `span.text[start : end]`. """Create a `Span` object from the slice `span.text[start : end]`.
start (int): The index of the first character of the span. start (int): The index of the first character of the span.
end (int): The index of the first character after the span. end (int): The index of the first character after the span.
label (uint64 or string): A label to attach to the Span, e.g. for label (Union[int, str]): A label to attach to the Span, e.g. for
named entities. named entities.
kb_id (uint64 or string): An ID from a KB to capture the meaning of a named entity. kb_id (Union[int, str]): An ID from a KB to capture the meaning of a named entity.
vector (ndarray[ndim=1, dtype='float32']): A meaning representation of vector (ndarray[ndim=1, dtype='float32']): A meaning representation of
the span. the span.
id (Union[int, str]): Unused.
alignment_mode (str): How character indices are aligned to token alignment_mode (str): How character indices are aligned to token
boundaries. Options: "strict" (character indices must be aligned boundaries. Options: "strict" (character indices must be aligned
with token boundaries), "contract" (span of all tokens completely with token boundaries), "contract" (span of all tokens completely
within the character span), "expand" (span of all tokens at least within the character span), "expand" (span of all tokens at least
partially covered by the character span). Defaults to "strict". partially covered by the character span). Defaults to "strict".
span_id (Union[int, str]): An identifier to associate with the span.
RETURNS (Span): The newly constructed object. RETURNS (Span): The newly constructed object.
""" """
start_idx += self.c.start_char start_idx += self.c.start_char
end_idx += self.c.start_char end_idx += self.c.start_char
return self.doc.char_span(start_idx, end_idx, label=label, kb_id=kb_id, vector=vector, alignment_mode=alignment_mode) return self.doc.char_span(start_idx, end_idx, label=label, kb_id=kb_id, vector=vector, alignment_mode=alignment_mode, span_id=span_id)
@property @property
def conjuncts(self): def conjuncts(self):

19
website/docs/api/doc.mdx
View File

@ -209,15 +209,16 @@ alignment mode `"strict".
> assert span.text == "New York" > assert span.text == "New York"
> ``` > ```
| Name | Description | | Name | Description |
| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ---------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `start` | The index of the first character of the span. ~~int~~ | | `start` | The index of the first character of the span. ~~int~~ |
| `end` | The index of the last character after 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]~~ | | `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ |
| `kb_id` | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ | | `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]~~ | | `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~~ | | `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~~ |
| **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~ | | `span_id` <Tag variant="new">3.3.1</Tag> | An identifier to associate with the span. ~~Union[int, str]~~ |
| **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~ |
## Doc.set_ents {id="set_ents",tag="method",version="3"} ## Doc.set_ents {id="set_ents",tag="method",version="3"}

2
website/docs/api/span.mdx
View File

@ -193,7 +193,9 @@ the character indices don't map to a valid span.
| `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ | | `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ |
| `kb_id` | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ | | `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]~~ | | `vector` | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~ |
| `id` | Unused. ~~Union[int, str]~~ |
| `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~~ | | `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~~ |
| `span_id` <Tag variant="new">3.5.1</Tag> | An identifier to associate with the span. ~~Union[int, str]~~ |
| **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~ | | **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~ |
## Span.similarity {id="similarity",tag="method",model="vectors"} ## Span.similarity {id="similarity",tag="method",model="vectors"}