explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-13 18:56:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

add test for span.sent when doc not parsed

Browse Source
This commit is contained in:
Thomas Opsomer 2018-02-15 16:59:16 +01:00
parent deab391cbf
commit 5d24a81c0b
1 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
spacy/tests/doc/test_span.py
View File

@ -19,6 +19,15 @@ def doc(en_tokenizer):
return get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps) return get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps)
@pytest.fixture
def doc_not_parsed(en_tokenizer):
text = "This is a sentence. This is another sentence. And a third."
tokens = en_tokenizer(text)
d = get_doc(tokens.vocab, [t.text for t in tokens])
d.is_parsed = False
return d
def test_spans_sent_spans(doc): def test_spans_sent_spans(doc):
sents = list(doc.sents) sents = list(doc.sents)
assert sents[0].start == 0 assert sents[0].start == 0
@ -34,6 +43,7 @@ def test_spans_root(doc):
assert span.root.text == 'sentence' assert span.root.text == 'sentence'
assert span.root.head.text == 'is' assert span.root.head.text == 'is'
def test_spans_string_fn(doc): def test_spans_string_fn(doc):
span = doc[0:4] span = doc[0:4]
assert len(span) == 4 assert len(span) == 4
@ -41,6 +51,7 @@ def test_spans_string_fn(doc):
assert span.upper_ == 'THIS IS A SENTENCE' assert span.upper_ == 'THIS IS A SENTENCE'
assert span.lower_ == 'this is a sentence' assert span.lower_ == 'this is a sentence'
def test_spans_root2(en_tokenizer): def test_spans_root2(en_tokenizer):
text = "through North and South Carolina" text = "through North and South Carolina"
heads = [0, 3, -1, -2, -4] heads = [0, 3, -1, -2, -4]
@ -49,12 +60,17 @@ def test_spans_root2(en_tokenizer):
assert doc[-2:].root.text == 'Carolina' assert doc[-2:].root.text == 'Carolina'
def test_spans_span_sent(doc): def test_spans_span_sent(doc, doc_not_parsed):
"""Test span.sent property""" """Test span.sent property"""
assert len(list(doc.sents)) assert len(list(doc.sents))
assert doc[:2].sent.root.text == 'is' assert doc[:2].sent.root.text == 'is'
assert doc[:2].sent.text == 'This is a sentence .' assert doc[:2].sent.text == 'This is a sentence .'
assert doc[6:7].sent.root.left_edge.text == 'This' assert doc[6:7].sent.root.left_edge.text == 'This'
# test on manual sbd
doc_not_parsed[0].is_sent_start = True
doc_not_parsed[5].is_sent_start = True
assert doc_not_parsed[1:3].sent == doc_not_parsed[0:5]
assert doc_not_parsed[10:14].sent == doc_not_parsed[5:]
def test_spans_lca_matrix(en_tokenizer): def test_spans_lca_matrix(en_tokenizer):