def test_core_is_not_written_in_extradata_if_article_is_non_core(app):
schema = load_schema('hep')
subschema = schema['properties']['arxiv_eprints']
categories_config = {
'ARXIV_CATEGORIES': {
'core': ['hep-ph'],
'non-core': ['astro-ph.CO', 'gr-qc']
}
}
with patch.dict(app.config, categories_config):
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
eng = MockEng()
obj.data = {
'arxiv_eprints': [
{
'categories': [
'astro-ph.CO',
],
'value': '1705.01122',
},
],
}
assert validate(obj.data['arxiv_eprints'], subschema) is None
set_core_in_extra_data(obj, eng)
assert 'core' not in obj.extra_data
def test_new_ticket_context_handles_unicode(unicode_data, extra_data, user):
obj = MockObj(unicode_data, extra_data)
ctx = new_ticket_context(user, obj)
assert isinstance(ctx['object'], MockObj)
assert ctx['email'] == '*****@*****.**'
assert ctx[
'subject'] == u'Your suggestion to INSPIRE: author Diego Martínez'
assert ctx['user_comment'] == 'Foo bar'
def test_is_experimental_paper():
obj = MockObj({'arxiv_eprints': [
{
'categories': ['hep-ex']
},
]}, {})
eng = MockEng()
assert is_experimental_paper(obj, eng)
def test_halt_record():
obj = MockObj({}, {'halt_action': 'foo', 'halt_message': 'bar'})
eng = MockEng()
default_halt_record = halt_record()
assert default_halt_record(obj, eng) is None
assert eng.action == 'foo'
assert eng.msg == 'bar'
def test_curation_ticket_context(data, extra_data, user):
obj = MockObj(data, extra_data)
ctx = curation_ticket_context(user, obj)
assert isinstance(ctx['object'], MockObj)
assert ctx['recid'] == 123
assert ctx['user_comment'] == 'Foo bar'
assert ctx['subject'] == 'Curation needed for author John Doe [John.Doe.1]'
assert ctx['email'] == '*****@*****.**'
assert ctx['record_url'] == 'http://example.com'
def test_arxiv_author_list_handles_multiple_author_xml_files():
schema = load_schema('hep')
eprints_subschema = schema['properties']['arxiv_eprints']
filename = pkg_resources.resource_filename(
__name__, os.path.join('fixtures', '1703.09986.multiple_author_lists.tar.gz'))
data = {
'$schema': 'http://localhost:5000/hep.json',
'arxiv_eprints': [
{
'categories': [
'hep-ex',
],
'value': '1703.09986',
},
],
} # record/1519995
validate(data['arxiv_eprints'], eprints_subschema)
extra_data = {}
files = MockFiles({
'1703.09986.tar.gz': AttrDict({
'file': AttrDict({
'uri': filename,
})
})
})
obj = MockObj(data, extra_data, files=files)
eng = MockEng()
default_arxiv_author_list = arxiv_author_list()
default_arxiv_author_list(obj, eng)
authors_subschema = schema['properties']['authors']
expected_authors = [
{
'affiliations': [{'value': 'Yerevan Phys. Inst.'}],
'ids': [
{'value': 'INSPIRE-00312131', 'schema': 'INSPIRE ID'},
{'value': 'CERN-432142', 'schema': 'CERN'},
],
'full_name': 'Sirunyan, Albert M',
},
{
'affiliations': [{'value': 'Yerevan Phys. Inst.'}],
'ids': [
{'value': 'INSPIRE-00312132', 'schema': 'INSPIRE ID'},
{'value': 'CERN-432143', 'schema': 'CERN'},
],
'full_name': 'Weary, Jake',
}
]
validate(expected_authors, authors_subschema)
assert obj.data.get('authors') == expected_authors
def test_preserve_root():
config = {'FEATURE_FLAG_ENABLE_MERGER': True}
with patch.dict(current_app.config, config):
obj = MockObj({'foo': 'bar'}, {})
eng = MockEng()
assert preserve_root(obj, eng) is None
assert obj.extra_data['merger_root'] == {'foo': 'bar'}
def test_set_exact_match_as_approved_in_extradata_no_exact_key_raises_exception(
):
data = {}
extra_data = {'matches': {'wrongkey': [1]}}
obj = MockObj(data, extra_data)
eng = MockEng()
with pytest.raises(KeyError):
set_exact_match_as_approved_in_extradata(obj, eng)
def test_guess_coreness_does_not_fail_when_request_fails(j_a_r, g_b_u):
j_a_r.side_effect = requests.exceptions.RequestException()
g_b_u.return_value = 'https://beard.inspirehep.net/predictor/coreness'
obj = MockObj({}, {})
eng = MockEng()
assert guess_coreness(obj, eng) is None
assert 'relevance_prediction' not in obj.extra_data
def test_set_exact_match_as_approved_in_extradata_with_empty_list_raises_exception(
):
data = {}
extra_data = {'matches': {'exact': []}}
obj = MockObj(data, extra_data)
eng = MockEng()
with pytest.raises(IndexError):
set_exact_match_as_approved_in_extradata(obj, eng)
def test_is_fuzzy_match_approved_returns_False_if_there_is_not_a_match_approved(
mock_match):
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
eng = MockEng()
assert not is_fuzzy_match_approved(obj, eng)
def test_is_fuzzy_match_approved_returns_true_if_there_is_a_match_approved(
mock_match):
data = {}
extra_data = {'fuzzy_match_approved_id': 4328}
obj = MockObj(data, extra_data)
eng = MockEng()
assert is_fuzzy_match_approved(obj, eng)
def test_guess_keywords_does_not_fail_when_request_fails(j_a_r, g_m_u):
j_a_r.side_effect = requests.exceptions.RequestException()
g_m_u.return_value = 'https://magpie.inspirehep.net/predict'
obj = MockObj({}, {})
eng = MockEng()
assert guess_keywords(obj, eng) is None
assert obj.extra_data == {}
def test_send_robotupload_update_authors_when_feature_flag_is_enabled():
with requests_mock.Mocker() as requests_mocker:
requests_mocker.register_uri(
'POST', 'http://inspirehep.net/batchuploader/robotupload/insert',
text='[INFO] foo bar baz'
)
config = {
'LEGACY_ROBOTUPLOAD_URL': 'http://inspirehep.net',
'PRODUCTION_MODE': True,
'FEATURE_FLAG_ENABLE_UPDATE_TO_LEGACY': True
}
with patch.dict(current_app.config, config), \
patch('inspirehep.modules.workflows.tasks.submission.record2marcxml'):
data = {
'$schema': 'http://localhost:5000/schemas/records/authors.json',
'name': {
'preferred_name': 'Jessica Jones',
'value': 'Jones, Jessica'
}
}
extra_data = {
'is-update': True
}
obj = MockObj(data, extra_data)
obj.workflow = MockWorkflow('author')
eng = MockEng(data_type='authors')
_send_robotupload = send_robotupload(
mode='insert',
)
assert _send_robotupload(obj, eng) is None
expected = (
'Robotupload sent!'
'[INFO] foo bar baz'
'end of upload'
)
result = obj.log._info.getvalue()
assert expected == result
def test_arxiv_plot_extract_is_safe_to_rerun(mock_os, tmpdir):
schema = load_schema('hep')
subschema = schema['properties']['arxiv_eprints']
filename = pkg_resources.resource_filename(
__name__, os.path.join('fixtures', '0804.1873.tar.gz'))
data = {
'arxiv_eprints': [
{
'categories': [
'nucl-ex',
],
'value': '0804.1873',
},
],
} # literature/783246
extra_data = {}
files = MockFiles({
'0804.1873.tar.gz':
AttrDict({
'file': AttrDict({
'uri': filename,
}),
}),
})
assert validate(data['arxiv_eprints'], subschema) is None
obj = MockObj(data, extra_data, files=files)
eng = MockEng()
temporary_dir = tmpdir.mkdir('plots')
mock_os.path.abspath.return_value = str(temporary_dir)
for _ in range(2):
assert arxiv_plot_extract(obj, eng) is None
expected_figures = [{
'url':
'/api/files/0b9dd5d1-feae-4ba5-809d-3a029b0bc110/figure1.png',
'source':
'arxiv',
'material':
'preprint',
'key':
'figure1.png',
'caption':
'Difference (in MeV) between the theoretical and experimental masses for the 2027 selected nuclei as a function of the mass number.'
}]
result = obj.data['figures']
assert expected_figures == result
expected_files = ['0804.1873.tar.gz', 'figure1.png']
assert expected_files == obj.files.keys
def test_curation_ticket_context():
data = {
'arxiv_eprints': [
{
'value': 'math.GT/0309136',
},
{
'value': '0706.0001v1',
},
],
'report_numbers': [
{
'value': 'foo',
},
],
'dois': [
{
'value': 'bar',
},
],
}
extra_data = {
'recid': 'baz',
'url': 'qux',
'formdata': {
'url': 'quux',
'references': [
'plugh',
],
'extra_comments': [
'xyzzy',
]
}
}
obj = MockObj(data, extra_data)
user = MockUser('*****@*****.**')
expected = {
'recid': 'baz',
'record_url': 'qux',
'link_to_pdf': 'quux',
'email': '*****@*****.**',
'references': [
'plugh',
],
'user_comment': [
'xyzzy',
],
'server_name': 'localhost:5000',
'subject': 'math.GT/0309136 arXiv:0706.0001v1 doi:bar foo (#baz)',
'legacy_url': 'https://old.inspirehep.net',
}
result = curation_ticket_context(user, obj)
assert expected == result
def test_pending_in_holding_pen_returns_true_if_something_matched(mock_match):
mock_match.return_value = iter([{'_id': 1}])
data = {}
extra_data = {}
obj = MockObj(data, extra_data, id=2)
eng = MockEng()
assert _pending_in_holding_pen(obj, eng)
def test_pending_in_holding_pen_returns_false_if_nothing_matched(mock_match):
mock_match.return_value = iter([])
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
eng = MockEng()
assert not _pending_in_holding_pen(obj, eng)
def test_set_exact_match_as_approved_in_extradata():
data = {}
extra_data = {'matches': {'exact': [1, 2]}}
obj = MockObj(data, extra_data)
eng = MockEng()
set_exact_match_as_approved_in_extradata(obj, eng)
assert get_value(obj.extra_data, 'matches.approved') is 1
def test_curation_ticket_context_handles_unicode(unicode_data, extra_data,
user):
obj = MockObj(unicode_data, extra_data)
ctx = curation_ticket_context(user, obj)
assert isinstance(ctx['object'], MockObj)
assert ctx['user_comment'] == 'Foo bar'
assert ctx[
'subject'] == u'Curation needed for author Diego Martínez [Diego.Martinez.Santos.1]'
assert ctx['email'] == '*****@*****.**'
assert ctx['record_url'] == 'http://example.com'
def test_fuzzy_match_returns_true_if_something_matched_with_publication_info(mock_match, enable_fuzzy_matcher):
schema = load_schema('hep')
publication_info_schema = schema['properties']['publication_info']
titles_schema = schema['properties']['titles']
matched_record = {
'control_number': 1472986,
'titles': [
{
'title': 'title',
},
],
'publication_info': [
{
'artid': '054021',
'journal_issue': '5',
'journal_title': 'Phys.Rev.D',
'journal_volume': '94',
'pubinfo_freetext': 'Phys. Rev. D94 (2016) 054021',
'year': 2016
},
],
}
assert validate(matched_record['titles'], titles_schema) is None
assert validate(matched_record['publication_info'], publication_info_schema) is None
mock_match.return_value = iter([{'_source': matched_record}])
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
eng = MockEng()
assert fuzzy_match(obj, eng)
assert 'matches' in obj.extra_data
expected = [{
'control_number': 1472986,
'title': 'title',
'publication_info': [
{
'artid': '054021',
'journal_issue': '5',
'journal_title': 'Phys.Rev.D',
'journal_volume': '94',
'pubinfo_freetext': 'Phys. Rev. D94 (2016) 054021',
'year': 2016
},
],
}]
result = get_value(obj.extra_data, 'matches.fuzzy')
assert expected == result
def test_set_refereed_and_fix_document_type_does_nothing_if_no_journals_were_found(mock_replace_refs):
mock_replace_refs.return_value = []
data = {'document_type': ['article']}
extra_data = {}
obj = MockObj(data, extra_data)
eng = MockEng()
assert set_refereed_and_fix_document_type(obj, eng) is None
assert 'refereed' not in obj.data
def test_wait_webcoll_does_nothing_otherwise():
config = {'PRODUCTION_MODE': False}
with patch.dict(current_app.config, config):
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
eng = MockEng()
assert wait_webcoll(obj, eng) is None
def test_fuzzy_matcher_run_on_feat_flag_enabled(enable_fuzzy_matcher):
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
eng = MockEng()
with patch('inspirehep.modules.workflows.tasks.matching.match') as match:
fuzzy_match(obj, eng)
match.assert_called()
def test_match_approval_gets_none():
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
ui_data = {'request_data': {'match_recid': None}}
result = MatchApproval.resolve(obj, ui_data)
assert not result
assert 'fuzzy_match_approved_id' in obj.extra_data
assert obj.extra_data['fuzzy_match_approved_id'] is None
def test_update_ticket_context(data, extra_data, user):
obj = MockObj(data, extra_data)
expected = {
'url': 'http://inspirehep.net/record/123',
'bibedit_url': 'http://inspirehep.net/record/123/edit',
'email': '*****@*****.**',
'user_comment': 'Foo bar',
'subject': 'Your update to author John Doe on INSPIRE',
}
ctx = update_ticket_context(user, obj)
assert ctx == expected
def test_update_ticket_context_handles_unicode(unicode_data, extra_data, user):
obj = MockObj(unicode_data, extra_data)
expected = {
'url': 'http://inspirehep.net/record/123',
'bibedit_url': 'http://inspirehep.net/record/123/edit',
'email': '*****@*****.**',
'user_comment': 'Foo bar',
'subject': u'Your update to author Diego Martínez on INSPIRE',
}
ctx = update_ticket_context(user, obj)
assert ctx == expected
def test_merge_approval():
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
obj.workflow.name = 'manual_merge'
result = MergeApproval.resolve(obj)
assert result
assert obj.extra_data['approved']
assert not obj.extra_data['auto-approved']
def test_match_approval_gets_match_recid():
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
ui_data = {'match_recid': 1234}
result = MatchApproval.resolve(obj, request_data=ui_data)
assert result
assert 'fuzzy_match_approved_id' in obj.extra_data
assert obj.extra_data['fuzzy_match_approved_id'] == 1234
def test_match_approval_nothing_sent_via_request():
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
result = MatchApproval.resolve(obj, None)
assert not result
assert 'fuzzy_match_approved_id' in obj.extra_data
assert obj.extra_data['fuzzy_match_approved_id'] is None
assert obj.status == ObjectStatus.RUNNING
def test_populate_journal_coverage_does_nothing_if_no_journal_is_found(mock_replace_refs):
mock_replace_refs.return_value = []
data = {}
extra_data = {}
obj = MockObj(data, extra_data)
eng = MockEng()
assert populate_journal_coverage(obj, eng) is None
assert 'journal_coverage' not in obj.extra_data
def test_send_robotupload_logs_on_error_response():
httpretty.HTTPretty.allow_net_connect = False
httpretty.register_uri(
httpretty.POST,
'http://inspirehep.net/batchuploader/robotupload/insert',
body='[ERROR] cannot use the service')
schema = load_schema('hep')
subschema = schema['properties']['arxiv_eprints']
config = {
'LEGACY_ROBOTUPLOAD_URL': 'http://inspirehep.net',
'PRODUCTION_MODE': True,
}
with patch.dict(current_app.config, config):
data = {
'arxiv_eprints': [
{
'categories': [
'hep-th',
],
'value': 'hep-th/9711200',
},
],
}
extra_data = {}
assert validate(data['arxiv_eprints'], subschema) is None
obj = MockObj(data, extra_data)
eng = MockEng()
_send_robotupload = send_robotupload(
marcxml_processor=hep2marc,
mode='insert',
)
with pytest.raises(Exception) as excinfo:
_send_robotupload(obj, eng)
expected = ('Error while submitting robotupload: '
'[ERROR] cannot use the service')
result = str(excinfo.value)
assert expected == result
expected = (
'Your IP is not in app.config_BATCHUPLOADER_WEB_ROBOT_RIGHTS on host: '
'[ERROR] cannot use the service')
result = obj.log._error.getvalue()
assert expected == result
httpretty.HTTPretty.allow_net_connect = True