aboutsummaryrefslogtreecommitdiffstats
path: root/tests/test_grobid_unstructured.py
blob: f36f9a4dbe5a6f779622f3ce351603e30da8f512 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
import pytest

from grobid_tei_xml import parse_citation_xml
from grobid_tei_xml.types import GrobidBiblio, GrobidAuthor

from fuzzycat.grobid_unstructured import grobid_api_process_citation, grobid_parse_unstructured, grobid_ref_to_release


def test_grobid_ref_to_release():

    d = GrobidBiblio(
        title="some title",
        doi='10.1234/5678',
        journal='some journal',
        authors=[
            GrobidAuthor(
                full_name='ahab sailor',
                given_name='ahab',
                surname='sailor',
            ),
            GrobidAuthor(full_name='mary jane', given_name='mary', surname='jane'),
        ],
    )
    r = grobid_ref_to_release(d)
    assert r.title == d.title
    assert r.ext_ids.doi == d.doi
    assert r.extra['container_name'] == d.journal
    assert r.contribs[0].surname == d.authors[0].surname
    assert r.contribs[1].raw_name == d.authors[1].full_name


def test_transform_grobid_ref_xml():
    """
    This used to be a test of the grobid2json file in this repository. Now it
    is a backwards compatibility test for grobid_tei_xml
    """
    citation_xml = """
<biblStruct >
    <analytic>
        <title level="a" type="main">Mesh migration following abdominal hernia repair: a comprehensive review</title>
        <author>
            <persName
                xmlns="http://www.tei-c.org/ns/1.0">
                <forename type="first">H</forename>
                <forename type="middle">B</forename>
                <surname>Cunningham</surname>
            </persName>
        </author>
        <author>
            <persName
                xmlns="http://www.tei-c.org/ns/1.0">
                <forename type="first">J</forename>
                <forename type="middle">J</forename>
                <surname>Weis</surname>
            </persName>
        </author>
        <author>
            <persName
                xmlns="http://www.tei-c.org/ns/1.0">
                <forename type="first">L</forename>
                <forename type="middle">R</forename>
                <surname>Taveras</surname>
            </persName>
        </author>
        <author>
            <persName
                xmlns="http://www.tei-c.org/ns/1.0">
                <forename type="first">S</forename>
                <surname>Huerta</surname>
            </persName>
        </author>
        <idno type="DOI">10.1007/s10029-019-01898-9</idno>
        <idno type="PMID">30701369</idno>
    </analytic>
    <monogr>
        <title level="j">Hernia</title>
        <imprint>
            <biblScope unit="volume">23</biblScope>
            <biblScope unit="issue">2</biblScope>
            <biblScope unit="page" from="235" to="243" />
            <date type="published" when="2019-01-30" />
        </imprint>
    </monogr>
</biblStruct>"""

    citation = parse_citation_xml(citation_xml)
    assert citation
    d = citation.to_legacy_dict()
    assert d['title'] == "Mesh migration following abdominal hernia repair: a comprehensive review"
    assert d['authors'][2]['given_name'] == "L"
    assert d['authors'][2]['surname'] == "Taveras"
    assert d['authors'][2]['name'] == "L R Taveras"
    assert d['doi'] == "10.1007/s10029-019-01898-9"
    assert d['pmid'] == "30701369"
    assert d['date'] == "2019-01-30"
    assert d['pages'] == "235-243"
    assert d['volume'] == "23"
    assert d['issue'] == "2"
    assert d['journal'] == "Hernia"


def test_grobid_parse_unstructured():
    """
    NOTE: this test makes live network requests to GROBID
    """

    r = grobid_parse_unstructured("blah")
    assert r is None

    r = grobid_parse_unstructured(
        """Cunningham HB, Weis JJ, Taveras LR, Huerta S. Mesh migration following abdominal hernia repair: a comprehensive review. Hernia. 2019 Apr;23(2):235-243. doi: 10.1007/s10029-019-01898-9. Epub 2019 Jan 30. PMID: 30701369."""
    )
    assert r.title == "Mesh migration following abdominal hernia repair: a comprehensive review"
    assert r.contribs[0].surname == "Cunningham"
    assert r.contribs[1].surname == "Weis"
    assert r.contribs[2].surname == "Taveras"
    assert r.contribs[3].surname == "Huerta"
    assert r.extra['container_name'] == "Hernia"
    assert r.release_year == 2019
    assert r.volume == "23"
    assert r.issue == "2"
    assert r.pages == "235-243"
    assert r.ext_ids.doi == "10.1007/s10029-019-01898-9"
    assert r.ext_ids.pmid == "30701369"


def test_grobid_parse_unstructured_timeout():
    """
    NOTE: this test makes live network requests to GROBID
    """
    with pytest.raises(TimeoutError):
        grobid_parse_unstructured("blah", timeout=0.000001)