spaCy/spacy/tests/lang/sv/test_noun_chunks.py

49 lines
1.8 KiB
Python
Raw Normal View History

import pytest
2020-09-21 21:43:54 +03:00
from spacy.tokens import Doc
2019-10-24 17:20:48 +03:00
def test_noun_chunks_is_parsed_sv(sv_tokenizer):
2020-09-29 22:39:28 +03:00
"""Test that noun_chunks raises Value Error for 'sv' language if Doc is not parsed."""
doc = sv_tokenizer("Studenten läste den bästa boken")
with pytest.raises(ValueError):
list(doc.noun_chunks)
SV_NP_TEST_EXAMPLES = [
(
"En student läste en bok", # A student read a book
["DET", "NOUN", "VERB", "DET", "NOUN"],
["det", "nsubj", "ROOT", "det", "dobj"],
2020-09-21 21:43:54 +03:00
[1, 2, 2, 4, 2],
["En student", "en bok"],
),
(
"Studenten läste den bästa boken.", # The student read the best book
["NOUN", "VERB", "DET", "ADJ", "NOUN", "PUNCT"],
["nsubj", "ROOT", "det", "amod", "dobj", "punct"],
2020-09-21 21:43:54 +03:00
[1, 1, 4, 4, 1, 1],
["Studenten", "den bästa boken"],
),
(
"De samvetslösa skurkarna hade stulit de största juvelerna på söndagen", # The remorseless crooks had stolen the largest jewels that sunday
["DET", "ADJ", "NOUN", "VERB", "VERB", "DET", "ADJ", "NOUN", "ADP", "NOUN"],
["det", "amod", "nsubj", "aux", "root", "det", "amod", "dobj", "case", "nmod"],
2020-09-21 21:43:54 +03:00
[2, 2, 4, 4, 4, 7, 7, 4, 9, 4],
["De samvetslösa skurkarna", "de största juvelerna", "på söndagen"],
),
]
@pytest.mark.parametrize(
"text,pos,deps,heads,expected_noun_chunks", SV_NP_TEST_EXAMPLES
)
def test_sv_noun_chunks(sv_tokenizer, text, pos, deps, heads, expected_noun_chunks):
tokens = sv_tokenizer(text)
assert len(heads) == len(pos)
2020-09-21 21:43:54 +03:00
words = [t.text for t in tokens]
doc = Doc(tokens.vocab, words=words, heads=heads, deps=deps, pos=pos)
noun_chunks = list(doc.noun_chunks)
assert len(noun_chunks) == len(expected_noun_chunks)
for i, np in enumerate(noun_chunks):
assert np.text == expected_noun_chunks[i]