mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
eddeb36c96
<!--- Provide a general summary of your changes in the title. --> ## Description - [x] Use [`black`](https://github.com/ambv/black) to auto-format all `.py` files. - [x] Update flake8 config to exclude very large files (lemmatization tables etc.) - [x] Update code to be compatible with flake8 rules - [x] Fix various small bugs, inconsistencies and messy stuff in the language data - [x] Update docs to explain new code style (`black`, `flake8`, when to use `# fmt: off` and `# fmt: on` and what `# noqa` means) Once #2932 is merged, which auto-formats and tidies up the CLI, we'll be able to run `flake8 spacy` actually get meaningful results. At the moment, the code style and linting isn't applied automatically, but I'm hoping that the new [GitHub Actions](https://github.com/features/actions) will let us auto-format pull requests and post comments with relevant linting information. ### Types of change enhancement, code style ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
64 lines
1.9 KiB
Python
64 lines
1.9 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import NOUN, PROPN, PRON, VERB, AUX
|
|
|
|
|
|
def noun_chunks(obj):
|
|
doc = obj.doc
|
|
if not len(doc):
|
|
return
|
|
np_label = doc.vocab.strings.add("NP")
|
|
left_labels = ["det", "fixed", "neg"] # ['nunmod', 'det', 'appos', 'fixed']
|
|
right_labels = ["flat", "fixed", "compound", "neg"]
|
|
stop_labels = ["punct"]
|
|
np_left_deps = [doc.vocab.strings.add(label) for label in left_labels]
|
|
np_right_deps = [doc.vocab.strings.add(label) for label in right_labels]
|
|
stop_deps = [doc.vocab.strings.add(label) for label in stop_labels]
|
|
token = doc[0]
|
|
while token and token.i < len(doc):
|
|
if token.pos in [PROPN, NOUN, PRON]:
|
|
left, right = noun_bounds(
|
|
doc, token, np_left_deps, np_right_deps, stop_deps
|
|
)
|
|
yield left.i, right.i + 1, np_label
|
|
token = right
|
|
token = next_token(token)
|
|
|
|
|
|
def is_verb_token(token):
|
|
return token.pos in [VERB, AUX]
|
|
|
|
|
|
def next_token(token):
|
|
try:
|
|
return token.nbor()
|
|
except IndexError:
|
|
return None
|
|
|
|
|
|
def noun_bounds(doc, root, np_left_deps, np_right_deps, stop_deps):
|
|
left_bound = root
|
|
for token in reversed(list(root.lefts)):
|
|
if token.dep in np_left_deps:
|
|
left_bound = token
|
|
right_bound = root
|
|
for token in root.rights:
|
|
if token.dep in np_right_deps:
|
|
left, right = noun_bounds(
|
|
doc, token, np_left_deps, np_right_deps, stop_deps
|
|
)
|
|
if list(
|
|
filter(
|
|
lambda t: is_verb_token(t) or t.dep in stop_deps,
|
|
doc[left_bound.i : right.i],
|
|
)
|
|
):
|
|
break
|
|
else:
|
|
right_bound = right
|
|
return left_bound, right_bound
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|