spaCy/spacy/lang/id/syntax_iterators.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* Remove unicode declarations

* Remove Python 3.5 and 2.7 from CI

* Don't require pathlib

* Replace compat helpers

* Remove OrderedDict

* Use f-strings

* Set Cython compiler language level

* Fix typo

* Re-add OrderedDict for Table

* Update setup.cfg

* Revert CONTRIBUTING.md

* Revert lookups.md

* Revert top-level.md

* Small adjustments and docs [ci skip]
2019-12-22 01:53:56 +01:00

47 lines
1.5 KiB
Python

from ...symbols import NOUN, PROPN, PRON
def noun_chunks(obj):
"""
Detect base noun phrases from a dependency parse. Works on both Doc and Span.
"""
labels = [
"nsubj",
"nsubj:pass",
"obj",
"iobj",
"ROOT",
"appos",
"nmod",
"nmod:poss",
]
doc = obj.doc # Ensure works on both Doc and Span.
np_deps = [doc.vocab.strings[label] for label in labels]
conj = doc.vocab.strings.add("conj")
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
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
yield word.left_edge.i, word.right_edge.i + 1, np_label
elif word.dep == conj:
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.right_edge.i + 1))
yield word.left_edge.i, word.right_edge.i + 1, np_label
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}