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.
59 lines
2.4 KiB
Python
59 lines
2.4 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import NOUN, PROPN, PRON
|
|
|
|
|
|
def noun_chunks(obj):
|
|
"""
|
|
Detect base noun phrases. Works on both Doc and Span.
|
|
"""
|
|
# It follows the logic of the noun chunks finder of English language,
|
|
# adjusted to some Greek language special characteristics.
|
|
# obj tag corrects some DEP tagger mistakes.
|
|
# Further improvement of the models will eliminate the need for this tag.
|
|
labels = ["nsubj", "obj", "iobj", "appos", "ROOT", "obl"]
|
|
doc = obj.doc # Ensure works on both Doc and Span.
|
|
np_deps = [doc.vocab.strings.add(label) for label in labels]
|
|
conj = doc.vocab.strings.add("conj")
|
|
nmod = doc.vocab.strings.add("nmod")
|
|
np_label = doc.vocab.strings.add("NP")
|
|
seen = set()
|
|
for i, word in enumerate(obj):
|
|
if word.pos not in (NOUN, PROPN, PRON):
|
|
continue
|
|
# Prevent nested chunks from being produced
|
|
if word.i in seen:
|
|
continue
|
|
if word.dep in np_deps:
|
|
if any(w.i in seen for w in word.subtree):
|
|
continue
|
|
flag = False
|
|
if word.pos == NOUN:
|
|
# check for patterns such as γραμμή παραγωγής
|
|
for potential_nmod in word.rights:
|
|
if potential_nmod.dep == nmod:
|
|
seen.update(
|
|
j for j in range(word.left_edge.i, potential_nmod.i + 1)
|
|
)
|
|
yield word.left_edge.i, potential_nmod.i + 1, np_label
|
|
flag = True
|
|
break
|
|
if flag is False:
|
|
seen.update(j for j in range(word.left_edge.i, word.i + 1))
|
|
yield word.left_edge.i, word.i + 1, np_label
|
|
elif word.dep == conj:
|
|
# covers the case: έχει όμορφα και έξυπνα παιδιά
|
|
head = word.head
|
|
while head.dep == conj and head.head.i < head.i:
|
|
head = head.head
|
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
|
if head.dep in np_deps:
|
|
if any(w.i in seen for w in word.subtree):
|
|
continue
|
|
seen.update(j for j in range(word.left_edge.i, word.i + 1))
|
|
yield word.left_edge.i, word.i + 1, np_label
|
|
|
|
|
|
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|