explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-14 05:37:03 +03:00
Code Issues Packages Projects Releases Wiki Activity

Allow passing a Span to displacy.parse_deps (#12477)

Browse Source 
* Allow passing a Span to displacy.parse_deps

* Update docstring

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Update API docs

---------

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
This commit is contained in:
Ye Lei (叶磊) 2023-03-31 15:44:01 +08:00 committed by GitHub
parent d85df9d577
commit ce258670b7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 21 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/displacy/__init__.py
View File

@ -125,13 +125,17 @@ def app(environ, start_response):
return [res] return [res]
def parse_deps(orig_doc: Doc, options: Dict[str, Any] = {}) -> Dict[str, Any]: def parse_deps(
orig_doc: Union[Doc, Span], options: Dict[str, Any] = {}
) -> Dict[str, Any]:
"""Generate dependency parse in {'words': [], 'arcs': []} format. """Generate dependency parse in {'words': [], 'arcs': []} format.
orig_doc (Doc): Document to parse. orig_doc (Union[Doc, Span]): Document to parse.
options (Dict[str, Any]): Dependency parse specific visualisation options. options (Dict[str, Any]): Dependency parse specific visualisation options.
RETURNS (dict): Generated dependency parse keyed by words and arcs. RETURNS (dict): Generated dependency parse keyed by words and arcs.
""" """
if isinstance(orig_doc, Span):
orig_doc = orig_doc.as_doc()
doc = Doc(orig_doc.vocab).from_bytes( doc = Doc(orig_doc.vocab).from_bytes(
orig_doc.to_bytes(exclude=["user_data", "user_hooks"]) orig_doc.to_bytes(exclude=["user_data", "user_hooks"])
) )

14
spacy/tests/test_displacy.py
View File

@ -275,6 +275,20 @@ def test_displacy_parse_deps(en_vocab):
{"start": 2, "end": 3, "label": "det", "dir": "left"}, {"start": 2, "end": 3, "label": "det", "dir": "left"},
{"start": 1, "end": 3, "label": "attr", "dir": "right"}, {"start": 1, "end": 3, "label": "attr", "dir": "right"},
] ]
# Test that displacy.parse_deps converts Span to Doc
deps = displacy.parse_deps(doc[:])
assert isinstance(deps, dict)
assert deps["words"] == [
{"lemma": None, "text": words[0], "tag": pos[0]},
{"lemma": None, "text": words[1], "tag": pos[1]},
{"lemma": None, "text": words[2], "tag": pos[2]},
{"lemma": None, "text": words[3], "tag": pos[3]},
]
assert deps["arcs"] == [
{"start": 0, "end": 1, "label": "nsubj", "dir": "left"},
{"start": 2, "end": 3, "label": "det", "dir": "left"},
{"start": 1, "end": 3, "label": "attr", "dir": "right"},
]
def test_displacy_invalid_arcs(): def test_displacy_invalid_arcs():

2
website/docs/api/top-level.mdx
View File

@ -291,7 +291,7 @@ the `manual=True` argument in `displacy.render`.
| Name | Description | | Name | Description |
| ----------- | ------------------------------------------------------------------- | | ----------- | ------------------------------------------------------------------- |
| `orig_doc` | Doc to parse dependencies. ~~Doc~~ | | `orig_doc` | Doc or span to parse dependencies. ~~Union[Doc, Span]~~ |
| `options` | Dependency parse specific visualisation options. ~~Dict[str, Any]~~ | | `options` | Dependency parse specific visualisation options. ~~Dict[str, Any]~~ |
| **RETURNS** | Generated dependency parse keyed by words and arcs. ~~dict~~ | | **RETURNS** | Generated dependency parse keyed by words and arcs. ~~dict~~ |