summaryrefslogtreecommitdiffstats
path: root/python/tests/import_arabesque.py
blob: 9483eb45249b4f8b534507675cde6aa7aa705914 (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

import json
import pytest
from fatcat_tools.importers import ArabesqueMatchImporter, SqlitePusher, JsonLinePusher
from fixtures import api


@pytest.fixture(scope="function")
def arabesque_importer(api):
    yield ArabesqueMatchImporter(api, extid_type="doi", crawl_id="DUMMY123")

# TODO: use API to check that entities actually created...
def test_arabesque_importer_basic(arabesque_importer):
    SqlitePusher(arabesque_importer, 'tests/files/arabesque_example.sqlite3', "crawl_result").run()

def test_arabesque_importer_json(arabesque_importer):
    with open('tests/files/arabesque_example.json', 'r') as f:
        JsonLinePusher(arabesque_importer, f).run()

def test_arabesque_importer(arabesque_importer):
    last_index = arabesque_importer.api.get_changelog(limit=1)[0].index
    arabesque_importer.bezerk_mode = True
    counts = SqlitePusher(arabesque_importer, 'tests/files/arabesque_example.sqlite3', "crawl_result").run()
    assert counts['insert'] == 1
    assert counts['exists'] == 0
    assert counts['skip'] == 490

    # fetch most recent editgroup
    change = arabesque_importer.api.get_changelog_entry(index=last_index+1)
    eg = change.editgroup
    assert eg.description
    assert "identifier/url seedlist" in eg.description.lower()
    assert eg.extra['git_rev']
    assert eg.extra['crawl_id'] == "DUMMY123"
    assert "fatcat_tools.ArabesqueMatchImporter" in eg.extra['agent']

    # re-insert; should skip
    arabesque_importer.reset()
    arabesque_importer.bezerk_mode = False
    counts = SqlitePusher(arabesque_importer, 'tests/files/arabesque_example.sqlite3', "crawl_result").run()
    assert counts['insert'] == 0
    assert counts['exists'] == 1
    assert counts['skip'] == 490

def test_arabesque_dict_parse(arabesque_importer):
    with open('tests/files/arabesque_example.json', 'r') as f:
        raw = json.loads(f.readline())
        f = arabesque_importer.parse_record(raw)
        assert f.sha1 == "bdd78be55800bb1c9a5e47005bac5e4124793c7b"
        assert f.mimetype == "application/pdf"
        assert len(f.urls) == 2
        for u in f.urls:
            if u.rel == "web":
                assert u.url.startswith("https://files.eccomasproceedia.org/")
            if u.rel == "webarchive":
                assert u.url.startswith("https://web.archive.org/")
        assert len(f.release_ids) == 1