aboutsummaryrefslogtreecommitdiffstats
path: root/python/tests/transform_elasticsearch.py
blob: 0d96e1395403e78dfe2edc95dcc5bde1c81e1871 (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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185

import json
import datetime

from fatcat_tools import *
from fatcat_openapi_client import *
from import_journal_metadata import journal_metadata_importer
from import_crossref import crossref_importer
from import_matched import matched_importer
from fixtures import *


def test_basic_elasticsearch_convert(crossref_importer):
    with open('tests/files/crossref-works.single.json', 'r') as f:
        # not a single line
        raw = json.loads(f.read())
        r = crossref_importer.parse_record(raw)
    r.state = 'active'
    release_to_elasticsearch(r)

def test_rich_elasticsearch_convert():
    r = ReleaseEntity(
        title="something",
        release_year=1234,
        license_slug="CC-BY-NC",
        ext_ids=ReleaseExtIds(),
        refs=[
            ReleaseRef(),
            ReleaseRef(target_release_id="iznnn644szdwva7khyxqzc73bi"),
        ],
    )
    r.state = 'active'
    r.container = ContainerEntity(
        name="dummy journal",
        extra={
            "ia": {
                "sim": {
                    "year_spans": [[1000, 1100]],
                },
            },
            "kbart": {
                "lockss": {
                    "year_spans": [[1200, 1300]],
                },
                "jstor": {
                    "year_spans": [[1950, 1960], [1980, 2005]],
                },
            },
            "sherpa_romeo": {"color": "blue"},
            "doaj": {"as_of": "2010-02-03"},
        },
    )
    r.files = [FileEntity(
        mimetype="application/pdf",
        urls=[
            FileUrl(rel="dweb", url="dat://a954329dlk/thingie"),
            FileUrl(rel="webarchive", url="https://web.archive.org/web/20001122030405/http://example.com"),
            FileUrl(rel="web", url="https://archive.org/details/blah/file.pdf"),
        ],
        extra={
            "shadows": {},
        },
    )]
    es = release_to_elasticsearch(r)
    assert es['release_year'] == r.release_year
    assert es['in_ia'] == True
    assert es['in_jstor'] == False
    assert es['in_ia_sim'] == False
    assert es['in_ia'] == True
    assert es['in_web'] == True
    assert es['in_dweb'] == True
    assert es['is_oa'] == True
    assert es['is_longtail_oa'] == False
    assert es['ref_count'] == 2
    assert es['ref_linked_count'] == 1

def test_elasticsearch_release_from_json():
    r = entity_from_json(open('./tests/files/release_etodop5banbndg3faecnfm6ozi.json', 'r').read(), ReleaseEntity)
    es = release_to_elasticsearch(r)

    assert es['subtitle'] == "Correpondence"
    assert es['ident'] == "etodop5banbndg3faecnfm6ozi"
    assert es['container_name'] == "BJOG: an International Journal of Obstetrics and Gynaecology"
    assert es['first_page'] == "1404"
    assert es['issue'] == "11"
    assert es['volume'] == "118"
    assert es['number'] == None
    assert es['in_ia_sim'] == True
    assert es['in_kbart'] == True

def test_elasticsearch_container_transform(journal_metadata_importer):
    with open('tests/files/journal_metadata.sample.json', 'r') as f:
        raw = json.loads(f.readline())
        c = journal_metadata_importer.parse_record(raw)
    c.state = 'active'
    es = container_to_elasticsearch(c)
    assert es['publisher'] == c.publisher

def test_elasticsearch_file_transform(matched_importer):
    f = entity_from_json(open('./tests/files/file_bcah4zp5tvdhjl5bqci2c2lgfa.json', 'r').read(), FileEntity)

    f.state = 'active'
    es = file_to_elasticsearch(f)
    assert es['sha1'] == f.sha1
    assert es['sha256'] == f.sha256
    assert es['md5'] == f.md5
    assert es['size_bytes'] == f.size
    assert es['mimetype'] == f.mimetype
    assert es['in_ia'] == True

    assert 'web' in es['rels']
    assert 'www.zhros.ru' in es['hosts']
    assert 'zhros.ru' in es['domains']
    assert 'archive.org' in (es['hosts'] + es['domains'])
    assert 'web.archive.org' in (es['hosts'] + es['domains'])
    # old regression
    assert not '.archive.org' in (es['hosts'] + es['domains'])

def test_elasticsearch_changelog_transform(matched_importer):
    ce = entity_from_json(open('./tests/files/changelog_3469683.json', 'r').read(), ChangelogEntry)

    es = changelog_to_elasticsearch(ce)
    assert es['index'] == 3469683
    # len("2020-01-30T05:04:39") => 19
    assert es['timestamp'][:19] == "2020-01-30T05:04:39.738601Z"[:19]
    assert es['editor_id'] == "scmbogxw25evtcesfcab5qaboa"
    assert es['username'] == "crawl-bot"
    assert es['is_bot'] == True
    assert es['is_admin'] == True
    assert es['agent'] == "fatcat_tools.IngestFileResultImporter"

    assert es['total'] == 50
    assert es['files'] == 50
    assert es['new_files'] == 50
    assert es['created'] == 50

    assert es['releases'] == 0
    assert es['new_releases'] == 0
    assert es['updated'] == 0
    assert es['deleted'] == 0

def test_elasticsearch_release_kbart_year():
    this_year = datetime.date.today().year
    r = ReleaseEntity(
        title="something",
        release_year=this_year,
        license_slug="CC-BY-NC",
        ext_ids=ReleaseExtIds(),
        refs=[
            ReleaseRef(),
            ReleaseRef(target_release_id="iznnn644szdwva7khyxqzc73bi"),
        ],
    )
    r.state = 'active'
    r.container = ContainerEntity(
        name="dummy journal",
        extra={
            "kbart": {
                "lockss": {
                    "year_spans": [[1900, this_year - 2]],
                },
            },
        },
    )
    es = release_to_elasticsearch(r)
    assert es['release_year'] == this_year
    assert es['in_ia'] == False
    assert es['in_kbart'] == False
    assert es['preservation'] == "none"

    r.container = ContainerEntity(
        name="dummy journal",
        extra={
            "kbart": {
                "lockss": {
                    "year_spans": [[1900, this_year - 1]],
                },
            },
        },
    )
    es = release_to_elasticsearch(r)
    assert es['release_year'] == this_year
    assert es['in_ia'] == False
    assert es['in_kbart'] == True
    assert es['preservation'] == "dark"