explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

failing test to reproduce overlapping spans problem

Browse Source
This commit is contained in:
svlandeg 2020-05-20 23:06:03 +02:00
parent 49ef06d793
commit 36a94c409a
1 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
spacy/tests/regression/test_issue5458.py Normal file
View File

@ -0,0 +1,21 @@
from spacy.lang.en import English
from spacy.lang.en.syntax_iterators import noun_chunks
from spacy.tests.util import get_doc
from spacy.vocab import Vocab
def test_issue5458():
# Test that the noun chuncker does not generate overlapping spans
words = ["In", "an", "era", "where", "markets", "have", "brought", "prosperity", "and", "empowerment", "."]
vocab = Vocab(strings=words)
dependencies = ["ROOT", "det", "pobj", "advmod", "nsubj", "aux", "relcl", "dobj", "cc", "conj", "punct"]
pos_tags = ["ADP", "DET", "NOUN", "ADV", "NOUN", "AUX", "VERB", "NOUN", "CCONJ", "NOUN", "PUNCT"]
heads = [0, 1, -2, 6, 2, 1, -4, -1, -1, -2, -10]
en_doc = get_doc(vocab, words, pos_tags, heads, dependencies)
en_doc.noun_chunks_iterator = noun_chunks
# if there are overlapping spans, this will fail with an E102 error "Can't merge non-disjoint spans"
nlp = English()
merge_nps = nlp.create_pipe("merge_noun_chunks")
merge_nps(en_doc)