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
133
134
135
136
137
138
139
140
141
142
143
|
import io
import pytest
from bs4 import BeautifulSoup
from fixtures import *
from fatcat_tools.importers import (
Bs4XmlLargeFilePusher,
DblpContainerImporter,
DblpReleaseImporter,
JsonLinePusher,
)
@pytest.fixture(scope="function")
def dblp_importer(api):
with open("tests/files/dblp_container_map.tsv", "r") as tsv_file:
yield DblpReleaseImporter(api, tsv_file, bezerk_mode=True)
@pytest.fixture(scope="function")
def dblp_container_importer(api):
with open("tests/files/dblp_container_map.tsv", "r") as tsv_file:
with open("tests/files/ISSN-to-ISSN-L.snip.txt", "r") as issn_file:
yield DblpContainerImporter(
api, issn_file, tsv_file, io.StringIO(), bezerk_mode=True
)
def test_dblp_importer(dblp_importer):
last_index = dblp_importer.api.get_changelog(limit=1)[0].index
with open("tests/files/example_dblp.xml", "rb") as f:
dblp_importer.bezerk_mode = True
counts = Bs4XmlLargeFilePusher(
dblp_importer, f, dblp_importer.ELEMENT_TYPES, use_lxml=True
).run()
# print(counts)
assert counts["insert"] == 3
assert counts["exists"] == 0
assert counts["skip"] == 1
# fetch most recent editgroup
change = dblp_importer.api.get_changelog_entry(index=last_index + 1)
eg = change.editgroup
assert eg.description
assert "dblp" in eg.description.lower()
assert eg.extra["git_rev"]
assert "fatcat_tools.DblpReleaseImporter" in eg.extra["agent"]
# check that entity name mangling was fixed on import
eg = dblp_importer.api.get_editgroup(eg.editgroup_id)
release = dblp_importer.api.get_release(eg.edits.releases[0].ident)
for r_edit in eg.edits.releases:
release = dblp_importer.api.get_release(r_edit.ident)
# print(release.ext_ids.dblp)
if release.ext_ids.dblp == "conf/er/Norrie08":
break
assert release.ext_ids.dblp == "conf/er/Norrie08"
assert release.contribs[0].raw_name == "Moira C. Norrie"
assert release.contribs[1].raw_name == "Michael H. Böhlen"
last_index = dblp_importer.api.get_changelog(limit=1)[0].index
with open("tests/files/example_dblp.xml", "rb") as f:
dblp_importer.bezerk_mode = False
dblp_importer.reset()
counts = Bs4XmlLargeFilePusher(
dblp_importer, f, dblp_importer.ELEMENT_TYPES, use_lxml=True
).run()
# print(counts)
assert counts["insert"] == 0
assert counts["exists"] == 3
assert counts["skip"] == 1
assert last_index == dblp_importer.api.get_changelog(limit=1)[0].index
def test_dblp_container_importer(dblp_container_importer):
last_index = dblp_container_importer.api.get_changelog(limit=1)[0].index
output_tsv_map = io.StringIO()
with open("tests/files/example_dblp_containers.json", "r") as f:
dblp_container_importer.bezerk_mode = True
dblp_container_importer.dblp_container_map_output = output_tsv_map
counts = JsonLinePusher(dblp_container_importer, f).run()
assert counts["insert"] == 10
assert counts["exists"] == 0
assert counts["skip"] == 0
# fetch most recent editgroup
change = dblp_container_importer.api.get_changelog_entry(index=last_index + 1)
eg = change.editgroup
assert eg.description
assert "dblp" in eg.description.lower()
assert eg.extra["git_rev"]
assert "fatcat_tools.DblpContainerImporter" in eg.extra["agent"]
# check that entity name mangling was fixed on import
eg = dblp_container_importer.api.get_editgroup(eg.editgroup_id)
for c_edit in eg.edits.containers:
container = dblp_container_importer.api.get_container(c_edit.ident)
if container.issnl == "1877-3273":
break
assert container.name == "Atlantis Thinking Machines"
assert container.issnl == "1877-3273"
assert container.container_type == "book-series"
assert container.extra["dblp"]["prefix"] == "series/atlantis"
assert container.extra["urls"] == ["http://link.springer.com/bookseries/10077"]
last_index = dblp_container_importer.api.get_changelog(limit=1)[0].index
output_tsv_map.seek(0)
# print(output_tsv_map.read())
# output_tsv_map.seek(0)
with open("tests/files/example_dblp_containers.json", "r") as f:
dblp_container_importer.reset()
dblp_container_importer.bezerk_mode = False
dblp_container_importer.dblp_container_map_output = io.StringIO()
dblp_container_importer.read_dblp_container_map_file(output_tsv_map)
counts = JsonLinePusher(dblp_container_importer, f).run()
print(counts)
assert counts["insert"] == 0
assert counts["exists"] == 10
assert counts["skip"] == 0
assert last_index == dblp_container_importer.api.get_changelog(limit=1)[0].index
def test_dblp_xml_parse(dblp_importer):
with open("tests/files/example_dblp_article.xml", "r") as f:
soup = BeautifulSoup(f, "xml")
r1 = dblp_importer.parse_record(soup.find_all("article")[0])
assert r1.title == "Jim Gray, astronomer"
assert r1.contribs[0].raw_name == "Alexander S. Szalay"
# tested above, in LXML import path
# assert r1.contribs[1].raw_name == "Michael H. Bohlen"
assert r1.contribs[2].raw_name == "Nicolas Heist"
# XXX: assert r1.contribs[2].extra['orcid'] == "0000-0002-4354-9138"
assert r1.contribs[3].raw_name == "Jens Lehmann"
assert r1.ext_ids.dblp == "journals/cacm/Szalay08"
assert r1.ext_ids.doi == "10.1145/1400214.1400231"
assert r1.pages == "58-65"
assert r1.issue == "11"
assert r1.volume == "51"
assert r1.release_year == 2008
# assert r1.extra['container_name'] == "Commun. ACM"
assert r1.extra["dblp"]["type"] == "article"
|
