mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-30 20:06:30 +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.
50 lines
1.5 KiB
Python
50 lines
1.5 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import NOUN, PROPN, PRON
|
|
|
|
|
|
def noun_chunks(obj):
|
|
"""
|
|
Detect base noun phrases from a dependency parse. Works on both Doc and Span.
|
|
"""
|
|
# this iterator extracts spans headed by NOUNs starting from the left-most
|
|
# syntactic dependent until the NOUN itself for close apposition and
|
|
# measurement construction, the span is sometimes extended to the right of
|
|
# the NOUN. Example: "eine Tasse Tee" (a cup (of) tea) returns "eine Tasse Tee"
|
|
# and not just "eine Tasse", same for "das Thema Familie".
|
|
labels = [
|
|
"sb",
|
|
"oa",
|
|
"da",
|
|
"nk",
|
|
"mo",
|
|
"ag",
|
|
"ROOT",
|
|
"root",
|
|
"cj",
|
|
"pd",
|
|
"og",
|
|
"app",
|
|
]
|
|
doc = obj.doc # Ensure works on both Doc and Span.
|
|
np_label = doc.vocab.strings.add("NP")
|
|
np_deps = set(doc.vocab.strings.add(label) for label in labels)
|
|
close_app = doc.vocab.strings.add("nk")
|
|
|
|
rbracket = 0
|
|
for i, word in enumerate(obj):
|
|
if i < rbracket:
|
|
continue
|
|
if word.pos in (NOUN, PROPN, PRON) and word.dep in np_deps:
|
|
rbracket = word.i + 1
|
|
# try to extend the span to the right
|
|
# to capture close apposition/measurement constructions
|
|
for rdep in doc[word.i].rights:
|
|
if rdep.pos in (NOUN, PROPN) and rdep.dep == close_app:
|
|
rbracket = rdep.i + 1
|
|
yield word.left_edge.i, rbracket, np_label
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|