def test_sentencizer_01(self):
text = shorten("""
It was common “along a tiny stream.” Argia apicalis.
""")
doc = NLP(text)
sents = list(doc.sents)
self.assertEqual(len(sents), 2)
def test_parse_11(self):
self.assertEqual(
FOREARM_LENGTH.parse(
shorten("""
sex=male ; unformatted measurements=126-54-10-16-7=18.7; FA 54
; hind foot with claw=10 mm; tragus length=7 mm;
tail length=54 mm; ear from notch=16 mm;
forearm length=54 mm; total length=126 mm""")),
[
{
"start": 36,
"end": 55,
"value": 7.0,
"units": "mm_shorthand",
"units_inferred": False,
"is_shorthand": True,
},
{
"start": 57,
"end": 62,
"units": None,
"value": 54.0,
"units_inferred": True,
},
{
"start": 153,
"end": 173,
"units": "mm",
"value": 54.0,
"units_inferred": False,
},
],
)
def test_sentencizer_06(self):
text = shorten("""
Capsules 8–15 × 6–12 mm, larger wings deltate-rounded, 10–17 mm wide,
smaller 3.5–5 mm wide. 2n = 34, 56 (South America).
""")
doc = NLP(text)
sents = list(doc.sents)
self.assertEqual(len(sents), 2)
def test_sentencizer_05(self):
text = shorten("""
Plants perennial (rhizomatous), usually glabrous, sometimes sparsely hairy.
Stems [10–]30–70[–100] cm. Leaves: stipules lanceolate to oblong.
""")
doc = NLP(text)
sents = list(doc.sents)
self.assertEqual(len(sents), 3)
def test_parse_108(self):
self.assertEqual(
TOTAL_LENGTH.parse(
shorten("""Body: 12 gm; Body and tail: 109 mm; Tail: 43 mm;
Hind Foot: 11 mm; Ear: 13 mm""")),
[
Trait(value=109,
units="mm",
units_inferred=False,
start=13,
end=34)
],
)
def test(text: str) -> List[Dict]:
"""Find entities in the doc."""
text = shorten(text)
doc = NLP(text)
traits = [e._.data for e in doc.ents]
# from pprint import pp
# pp(traits, compact=True)
# from spacy import displacy
# displacy.serve(doc, options={'collapse_punct': False, 'compact': True})
return traits
def test_traits(text: str) -> List[Dict]:
"""Find entities in the doc."""
text = shorten(text)
text = clean_text(text, trans=TRANS)
doc = NLP(text)
traits = [e._.data for e in doc.ents]
# from pprint import pp
# pp(traits)
# from spacy import displacy
# options = {'collapse_punct': False, 'compact': True}
# displacy.serve(doc, options=options)
return traits
def test_parse_07(self):
self.assertEqual(
TRAGUS_LENGTH.parse(
shorten(
"""
{"measurements":"78-39-5-14-8(TR)-30(FA)",
"weightInGrams":"3.5" }"""
)
),
[
{
"start": 17,
"end": 40,
"value": 8.0,
"units": "mm_shorthand",
"units_inferred": False,
"is_shorthand": True,
}
],
)
def test_parse_06(self):
self.assertEqual(
TRAGUS_LENGTH.parse(
shorten(
"""
sex=male ; unformatted measurements=126-54-10-16-7=18.7; FA 54
; hind foot with claw=10 mm; tragus length=7 mm;
tail length=54 mm; ear from notch=16 mm;
forearm length=54 mm; total length=126 mm"""
)
),
[
{
"start": 92,
"end": 110,
"units": "mm",
"value": 7.0,
"units_inferred": False,
}
],
)
def test(text: str) -> List[Dict]:
"""Find entities in the doc."""
text = shorten(text)
return TEST.test_traits(text)
def test_sentencizer_02(self):
text = shorten("""(Dunn et al. 2009, Jørgensen 2015).""")
doc = NLP(text)
sents = list(doc.sents)
self.assertEqual(len(sents), 1)
def test_parse_109(self):
self.assertEqual(
TOTAL_LENGTH.parse(
shorten("""Note in catalog: Recatalogued from 115818-850""")),
[],
)
def test_parse_107(self):
self.assertEqual(TOTAL_LENGTH.parse(shorten("""Body: 14 g""")), [])