From cdfd6b85b386b7bbf9d5a5179ef26970b6e5a4e7 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 2 Nov 2021 18:13:14 -0700 Subject: fmt (black): tests/ --- python/tests/import_jstor.py | 49 ++++++++++++++++++++++++++------------------ 1 file changed, 29 insertions(+), 20 deletions(-) (limited to 'python/tests/import_jstor.py') diff --git a/python/tests/import_jstor.py b/python/tests/import_jstor.py index 270da3ec..8ad550b3 100644 --- a/python/tests/import_jstor.py +++ b/python/tests/import_jstor.py @@ -1,4 +1,3 @@ - import pytest from bs4 import BeautifulSoup from fixtures import * @@ -8,48 +7,58 @@ from fatcat_tools.importers import Bs4XmlFilePusher, JstorImporter @pytest.fixture(scope="function") def jstor_importer(api): - with open('tests/files/ISSN-to-ISSN-L.snip.txt', 'r') as issn_file: - yield JstorImporter(api, issn_file, extid_map_file='tests/files/example_map.sqlite3', bezerk_mode=True) + with open("tests/files/ISSN-to-ISSN-L.snip.txt", "r") as issn_file: + yield JstorImporter( + api, issn_file, extid_map_file="tests/files/example_map.sqlite3", bezerk_mode=True + ) + @pytest.fixture(scope="function") def jstor_importer_existing(api): - with open('tests/files/ISSN-to-ISSN-L.snip.txt', 'r') as issn_file: - yield JstorImporter(api, issn_file, extid_map_file='tests/files/example_map.sqlite3', bezerk_mode=False) + with open("tests/files/ISSN-to-ISSN-L.snip.txt", "r") as issn_file: + yield JstorImporter( + api, issn_file, extid_map_file="tests/files/example_map.sqlite3", bezerk_mode=False + ) + def test_jstor_importer(jstor_importer): last_index = jstor_importer.api.get_changelog(limit=1)[0].index - with open('tests/files/jstor-article-10.2307_111039.xml', 'r') as f: + with open("tests/files/jstor-article-10.2307_111039.xml", "r") as f: jstor_importer.bezerk_mode = True counts = Bs4XmlFilePusher(jstor_importer, f, "article").run() - assert counts['insert'] == 1 - assert counts['exists'] == 0 - assert counts['skip'] == 0 + assert counts["insert"] == 1 + assert counts["exists"] == 0 + assert counts["skip"] == 0 # fetch most recent editgroup - change = jstor_importer.api.get_changelog_entry(index=last_index+1) + change = jstor_importer.api.get_changelog_entry(index=last_index + 1) eg = change.editgroup assert eg.description assert "jstor" in eg.description.lower() - assert eg.extra['git_rev'] - assert "fatcat_tools.JstorImporter" in eg.extra['agent'] + assert eg.extra["git_rev"] + assert "fatcat_tools.JstorImporter" in eg.extra["agent"] last_index = jstor_importer.api.get_changelog(limit=1)[0].index - with open('tests/files/jstor-article-10.2307_111039.xml', 'r') as f: + with open("tests/files/jstor-article-10.2307_111039.xml", "r") as f: jstor_importer.bezerk_mode = False jstor_importer.reset() counts = Bs4XmlFilePusher(jstor_importer, f, "article").run() - assert counts['insert'] == 0 - assert counts['exists'] == 1 - assert counts['skip'] == 0 + assert counts["insert"] == 0 + assert counts["exists"] == 1 + assert counts["skip"] == 0 assert last_index == jstor_importer.api.get_changelog(limit=1)[0].index + def test_jstor_xml_parse(jstor_importer): - with open('tests/files/jstor-article-10.2307_111039.xml', 'r') as f: + with open("tests/files/jstor-article-10.2307_111039.xml", "r") as f: soup = BeautifulSoup(f, "xml") r = jstor_importer.parse_record(soup.find_all("article")[0]) print(r.extra) - assert r.title == "On the Universal Law of Attraction, Including that of Gravitation, as a Particular Case of Approximation Deducible from the Principle that Equal and Similar Particles of Matter Move Similarly, Relatively to Each other. [Abstract]" + assert ( + r.title + == "On the Universal Law of Attraction, Including that of Gravitation, as a Particular Case of Approximation Deducible from the Principle that Equal and Similar Particles of Matter Move Similarly, Relatively to Each other. [Abstract]" + ) assert r.subtitle is None assert r.original_title is None assert r.publisher == "The Royal Society" @@ -66,9 +75,9 @@ def test_jstor_xml_parse(jstor_importer): assert r.release_date is None assert r.release_year == 1843 # matched by ISSN, so shouldn't be in there? - #assert extra['container_name'] == "Abstracts of the Papers Communicated to the Royal Society of London" + # assert extra['container_name'] == "Abstracts of the Papers Communicated to the Royal Society of London" assert len(r.contribs) == 1 - assert r.extra['jstor']['journal_ids'] == ['abstpapecommroya', 'j100687'] + assert r.extra["jstor"]["journal_ids"] == ["abstpapecommroya", "j100687"] assert r.contribs[0].raw_name == "John Kinnersley Smythies" assert r.contribs[0].given_name == "John Kinnersley" -- cgit v1.2.3