def test_upload_secure_session():
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
s = get_session(config={'general': {'secure': True}})
rsps.add_metadata_mock('nasa')
item = s.get_item('nasa')
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.PUT, S3_URL_RE)
r = item.upload(NASA_METADATA_PATH)
assert r[0].url == 'https://s3.us.archive.org/nasa/nasa.json'
def test_ia_upload_keep_directories(tmpdir_ch, caplog):
os.mkdir('foo')
with open('foo/test.txt', 'w') as fh:
fh.write('foo')
with open('test.csv', 'w') as fh:
fh.write('identifier,file\n')
fh.write('nasa,foo/test.txt\n')
# Default behaviour
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
rsps.add(responses.PUT,
f'{PROTOCOL}//s3.us.archive.org/nasa/test.txt',
body='',
content_type='text/plain')
ia_call(['ia', '--log', 'upload', 'nasa', 'foo/test.txt'])
assert f'uploaded test.txt to {PROTOCOL}//s3.us.archive.org/nasa/test.txt' in caplog.text
caplog.clear()
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
rsps.add(responses.PUT,
f'{PROTOCOL}//s3.us.archive.org/nasa/test.txt',
body='',
content_type='text/plain')
ia_call(['ia', '--log', 'upload', '--spreadsheet', 'test.csv'])
assert f'uploaded test.txt to {PROTOCOL}//s3.us.archive.org/nasa/test.txt' in caplog.text
caplog.clear()
# With the option
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
rsps.add(responses.PUT,
f'{PROTOCOL}//s3.us.archive.org/nasa/foo/test.txt',
body='',
content_type='text/plain')
ia_call([
'ia', '--log', 'upload', 'nasa', 'foo/test.txt',
'--keep-directories'
])
assert f'uploaded foo/test.txt to {PROTOCOL}//s3.us.archive.org/nasa/foo/test.txt' in caplog.text
caplog.clear()
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
rsps.add(responses.PUT,
f'{PROTOCOL}//s3.us.archive.org/nasa/foo/test.txt',
body='',
content_type='text/plain')
ia_call([
'ia', '--log', 'upload', '--spreadsheet', 'test.csv',
'--keep-directories'
])
assert f'uploaded foo/test.txt to {PROTOCOL}//s3.us.archive.org/nasa/foo/test.txt' in caplog.text
def test_download(tmpdir, nasa_item):
tmpdir.chdir()
with IaRequestsMock() as rsps:
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='test content')
nasa_item.download(files='nasa_meta.xml')
assert len(tmpdir.listdir()) == 1
with IaRequestsMock() as rsps:
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='new test content')
nasa_item.download(files='nasa_meta.xml')
with open('nasa/nasa_meta.xml', 'r') as fh:
assert fh.read() == 'new test content'
def test_upload_delete(tmpdir, nasa_item):
body = (
"<?xml version='1.0' encoding='UTF-8'?>"
'<Error><Code>BadDigest</Code><Message>The Content-MD5 you specified did not '
'match what we received.</Message><Resource>content-md5 submitted with PUT: '
'foo != received data md5: 70871f9fce8dd23853d6e42417356b05also not equal to '
'base64 version: cIcfn86N0jhT1uQkFzVrBQ==</Resource><RequestId>ec03fe7c-e123-'
'4133-a207-3141d4d74096</RequestId></Error>')
_expected_headers = deepcopy(EXPECTED_S3_HEADERS)
del _expected_headers['x-archive-meta00-scanner']
tmpdir.chdir()
test_file = os.path.join(str(tmpdir), 'test.txt')
with open(test_file, 'w') as fh:
fh.write('test delete')
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
# Non-matching md5, should not delete.
rsps.add(responses.PUT,
S3_URL_RE,
body=body,
adding_headers=_expected_headers,
status=400)
with pytest.raises(HTTPError):
nasa_item.upload(test_file,
access_key='a',
secret_key='b',
delete=True,
queue_derive=True)
assert len(tmpdir.listdir()) == 1
_expected_headers = deepcopy(EXPECTED_S3_HEADERS)
test_file = os.path.join(str(tmpdir), 'test.txt')
with open(test_file, 'w') as fh:
fh.write('test delete')
# Matching md5, should delete.
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.PUT, S3_URL_RE, adding_headers=_expected_headers)
resp = nasa_item.upload(test_file,
access_key='a',
secret_key='b',
delete=True,
queue_derive=True)
for r in resp:
headers = {k.lower(): str(v) for k, v in r.headers.items()}
del headers['content-type']
assert headers == _expected_headers
assert len(tmpdir.listdir()) == 0
def test_ia_list_columns(capsys):
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
ia_list.main(['list', '--columns', 'name,md5', '--glob', '*meta.xml', 'nasa'],
SESSION)
out, err = capsys.readouterr()
assert out == 'nasa_meta.xml\t0e339f4a29a8bc42303813cbec9243e5\n'
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
ia_list.main(['list', '--columns', 'md5', '--glob', '*meta.xml', 'nasa'], SESSION)
out, err = capsys.readouterr()
assert out == '0e339f4a29a8bc42303813cbec9243e5\n'
def test_search_items_fts(session):
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.POST,
'{0}//be-api.us.archive.org/ia-pub-fts-api'.format(PROTOCOL),
body=TEST_SCRAPE_RESPONSE)
rsps.add_metadata_mock('nasa')
r = search_items('nina simone',
full_text_search=True,
archive_session=session)
print(r.search_url)
assert r.fts == True
assert r.dsl_fts == False
assert r.query == '!L nina simone'
assert r.params == {'count': 10000, 'q': '!L nina simone'}
r = search_items('nina simone',
full_text_search=True,
dsl_fts=True,
archive_session=session)
assert r.fts == True
assert r.dsl_fts == True
assert r.query == 'nina simone'
assert r.params == {'count': 10000, 'q': 'nina simone'}
r = search_items('nina simone', dsl_fts=True, archive_session=session)
assert r.fts == True
assert r.dsl_fts == True
assert r.query == 'nina simone'
assert r.params == {'count': 10000, 'q': 'nina simone'}
def test_upload_validate_identifier():
try:
upload('føø',
NASA_METADATA_PATH,
access_key='test_access',
secret_key='test_secret',
validate_identifier=True)
assert False
except Exception as exc:
assert isinstance(exc, InvalidIdentifierException)
expected_s3_headers = {
'content-length': '7557',
'x-archive-queue-derive': '1',
'x-archive-meta00-scanner':
'uri(Internet%20Archive%20Python%20library',
'x-archive-size-hint': '7557',
'x-archive-auto-make-bucket': '1',
'authorization': 'LOW test_access:test_secret',
}
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.PUT,
re.compile(r'.*s3.us.archive.org/.*'),
adding_headers=expected_s3_headers)
rsps.add_metadata_mock('nasa')
rsps.add(responses.GET,
'{0}//archive.org/metadata/nasa'.format(PROTOCOL),
body='{}')
upload('nasa',
NASA_METADATA_PATH,
access_key='test_access',
secret_key='test_secret',
validate_identifier=True)
assert True
def test_upload_dir(tmpdir, nasa_item):
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.PUT, S3_URL_RE, adding_headers=EXPECTED_S3_HEADERS)
tmpdir.mkdir('dir_test')
with open(os.path.join(str(tmpdir), 'dir_test', 'foo.txt'), 'w') as fh:
fh.write('hi')
with open(os.path.join(str(tmpdir), 'dir_test', 'foo2.txt'),
'w') as fh:
fh.write('hi 2')
# Test no-slash upload, dir is not in key name.
_responses = nasa_item.upload(os.path.join(str(tmpdir), 'dir_test') +
'/',
access_key='a',
secret_key='b')
expected_eps = [
f'{S3_URL}nasa/foo.txt',
f'{S3_URL}nasa/foo2.txt',
]
for resp in _responses:
assert resp.request.url in expected_eps
# Test slash upload, dir is in key name.
_responses = nasa_item.upload(os.path.join(str(tmpdir), 'dir_test'),
access_key='a',
secret_key='b')
tmp_path = norm_filepath(str(tmpdir))
expected_eps = [
f'{S3_URL}nasa{tmp_path}/dir_test/foo.txt',
f'{S3_URL}nasa{tmp_path}/dir_test/foo2.txt',
]
for resp in _responses:
assert resp.request.url in expected_eps
def test_upload_checksum(tmpdir, nasa_item):
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
nasa_item = get_item('nasa')
_expected_headers = deepcopy(EXPECTED_S3_HEADERS)
del _expected_headers['x-archive-meta00-scanner']
test_file = os.path.join(str(tmpdir), 'checksum_test.txt')
with open(test_file, 'wb') as fh:
fh.write(b'test delete')
# No skip.
rsps.add(responses.PUT, S3_URL_RE, adding_headers=_expected_headers)
resp = nasa_item.upload(test_file,
access_key='a',
secret_key='b',
checksum=True)
for r in resp:
headers = dict((k.lower(), str(v)) for k, v in r.headers.items())
del headers['content-type']
assert headers == _expected_headers
assert r.status_code == 200
# Skip.
nasa_item.item_metadata['files'].append(
dict(name='checksum_test.txt',
md5='33213e7683c1e6d15b2a658f3c567717'))
resp = nasa_item.upload(test_file,
access_key='a',
secret_key='b',
checksum=True)
for r in resp:
headers = dict((k.lower(), str(v)) for k, v in r.headers.items())
assert r.status_code is None
def test_search_items(session):
results_url = (
'{0}//archive.org/services/search/v1/scrape'
'?q=identifier%3Anasa&count=10000&REQUIRE_AUTH=true'.format(PROTOCOL))
count_url = ('{0}//archive.org/services/search/v1/scrape'
'?q=identifier%3Anasa&total_only=true&REQUIRE_AUTH=true'
'&count=10000'.format(PROTOCOL))
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.POST,
results_url,
body=TEST_SCRAPE_RESPONSE,
match_querystring=True)
rsps.add(responses.POST,
count_url,
body='{"items":[],"count":0,"total":1}',
match_querystring=True,
content_type='application/json; charset=UTF-8')
r = search_items('identifier:nasa', archive_session=session)
expected_results = [{'identifier': 'nasa'}]
assert r.num_found == 1
assert iter(r).search == r
assert len(iter(r)) == 1
assert len(r.iter_as_results()) == 1
assert list(r) == expected_results
assert list(r.iter_as_results()) == expected_results
def test_download_checksum(tmpdir, caplog):
tmpdir.chdir()
# test overwrite based on checksum.
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='test content')
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='overwrite based on md5')
nasa_item = get_item('nasa')
nasa_item.download(files='nasa_meta.xml')
nasa_item.download(files='nasa_meta.xml', checksum=True)
assert load_file('nasa/nasa_meta.xml') == 'overwrite based on md5'
# test no overwrite based on checksum.
rsps.reset()
rsps.add(responses.GET,
DOWNLOAD_URL_RE,
body=load_test_data_file('nasa_meta.xml'))
nasa_item.download(files='nasa_meta.xml', checksum=True)
nasa_item.download(files='nasa_meta.xml', checksum=True)
assert 'skipping nasa' in caplog.text
assert 'nasa_meta.xml, file already exists based on checksum.' in caplog.text
def test_upload():
expected_s3_headers = {
'content-length': '7557',
'x-archive-queue-derive': '1',
'x-archive-meta00-scanner': 'uri(Internet%20Archive%20Python%20library',
'x-archive-size-hint': '7557',
'content-md5': '6f1834f5c70c0eabf93dea675ccf90c4',
'x-archive-auto-make-bucket': '1',
'authorization': 'LOW test_access:test_secret',
}
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.PUT, re.compile(r'.*s3.us.archive.org/.*'),
adding_headers=expected_s3_headers)
rsps.add_metadata_mock('nasa')
rsps.add(responses.GET, '{0}//archive.org/metadata/nasa'.format(PROTOCOL),
body='{}')
_responses = upload('nasa', NASA_METADATA_PATH,
access_key='test_access',
secret_key='test_secret')
for response in _responses:
req = response.request
headers = dict((k.lower(), str(v)) for k, v in req.headers.items())
scanner_header = '%20'.join(
response.headers['x-archive-meta00-scanner'].split('%20')[:4])
headers['x-archive-meta00-scanner'] = scanner_header
assert headers == expected_s3_headers
assert req.url == '{0}//s3.us.archive.org/nasa/nasa.json'.format(PROTOCOL)
def test_upload_503(capsys, nasa_item):
body = (
"<?xml version='1.0' encoding='UTF-8'?>"
'<Error><Code>SlowDown</Code><Message>Please reduce your request rate.'
'</Message><Resource>simulated error caused by x-(amz|archive)-simulate-error'
', try x-archive-simulate-error:help</Resource><RequestId>d36ec445-8d4a-4a64-'
'a110-f67af6ee2c2a</RequestId></Error>')
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
_expected_headers = deepcopy(EXPECTED_S3_HEADERS)
rsps.add(responses.GET, S3_URL_RE, body='{"over_limit": "1"}')
rsps.add(responses.PUT,
S3_URL_RE,
body=body,
adding_headers=_expected_headers,
status=503)
try:
nasa_item.upload(NASA_METADATA_PATH,
access_key='a',
secret_key='b',
retries=1,
retries_sleep=.1,
verbose=True)
except Exception as exc:
assert 'Please reduce your request rate' in str(exc)
out, err = capsys.readouterr()
assert 'warning: s3 is overloaded' in err
def test_download_io_error(tmpdir, nasa_item):
tmpdir.chdir()
with IaRequestsMock() as rsps:
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='test content')
nasa_item.download(files='nasa_meta.xml')
with pytest.raises(ConnectionError):
nasa_item.download(files='nasa_meta.xml')
def test_upload_metadata(nasa_item):
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
_expected_headers = deepcopy(EXPECTED_S3_HEADERS)
del _expected_headers['x-archive-meta00-scanner']
_expected_headers['x-archive-meta00-foo'] = 'bar'
_expected_headers['x-archive-meta00-subject'] = 'first'
_expected_headers['x-archive-meta01-subject'] = 'second'
_expected_headers['x-archive-meta00-baz'] = (
'uri(%D0%9F%D0%BE%D1%87%D0%B5%D0%BC'
'%D1%83%20%D0%B1%D1%8B%20%D0%B8%20%'
'D0%BD%D0%B5%D1%82...)')
_expected_headers['x-archive-meta00-baz2'] = (
'uri(%D0%9F%D0%BE%D1%87%D0%B5%D0%BC'
'%D1%83%20%D0%B1%D1%8B%20%D0%B8%20%'
'D0%BD%D0%B5%D1%82...)')
rsps.add(responses.PUT, S3_URL_RE,
adding_headers=_expected_headers)
md = dict(
foo='bar',
subject=['first', 'second'],
baz='Почему бы и нет...',
baz2=(u'\u041f\u043e\u0447\u0435\u043c\u0443 \u0431\u044b \u0438 '
u'\u043d\u0435\u0442...'),
)
_responses = nasa_item.upload(NASA_METADATA_PATH,
metadata=md,
access_key='a',
secret_key='b')
for resp in _responses:
request = resp.request
del request.headers['x-archive-meta00-scanner']
headers = dict((k.lower(), str(v)) for k, v in request.headers.items())
assert 'user-agent' in headers
del headers['user-agent']
assert headers == _expected_headers
def test_ia_upload_checksum(tmpdir_ch, caplog):
with open('test.txt', 'w') as fh:
fh.write('foo')
# First upload, file not in metadata yet
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
rsps.add(responses.PUT,
f'{PROTOCOL}//s3.us.archive.org/nasa/test.txt',
body='',
content_type='text/plain')
ia_call(['ia', '--log', 'upload', 'nasa', 'test.txt', '--checksum'])
assert f'uploaded test.txt to {PROTOCOL}//s3.us.archive.org/nasa/test.txt' in caplog.text
caplog.clear()
# Second upload with file in metadata
def insert_test_txt(body):
body = json.loads(body)
body['files'].append({
'name': 'test.txt',
'md5': 'acbd18db4cc2f85cedef654fccc4a4d8'
})
return json.dumps(body)
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa', transform_body=insert_test_txt)
ia_call(['ia', '--log', 'upload', 'nasa', 'test.txt', '--checksum'],
expected_exit_code=1)
assert f'test.txt already exists: {PROTOCOL}//s3.us.archive.org/nasa/test.txt' in caplog.text
caplog.clear()
# Second upload with spreadsheet
with open('test.csv', 'w') as fh:
fh.write('identifier,file\n')
fh.write('nasa,test.txt\n')
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa', transform_body=insert_test_txt)
ia_call([
'ia', '--log', 'upload', '--spreadsheet', 'test.csv', '--checksum'
],
expected_exit_code=1)
assert f'test.txt already exists: {PROTOCOL}//s3.us.archive.org/nasa/test.txt' in caplog.text
def test_download_no_directory(tmpdir, nasa_item):
url_re = re.compile(f'{PROTOCOL}//archive.org/download/.*')
tmpdir.chdir()
with IaRequestsMock() as rsps:
rsps.add(responses.GET, url_re, body='no dest dir')
nasa_item.download(files='nasa_meta.xml', no_directory=True)
with open(os.path.join(str(tmpdir), 'nasa_meta.xml'), 'r') as fh:
assert fh.read() == 'no dest dir'
def test_download_clobber(tmpdir, nasa_item):
tmpdir.chdir()
with IaRequestsMock() as rsps:
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='test content')
nasa_item.download(files='nasa_meta.xml')
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='new test content')
nasa_item.download(files='nasa_meta.xml')
load_file('nasa/nasa_meta.xml') == 'new test content'
def test_search_items_as_items():
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.POST,
'{0}//archive.org/services/search/v1/scrape'.format(PROTOCOL),
body=TEST_SCRAPE_RESPONSE)
rsps.add_metadata_mock('nasa')
r = search_items('identifier:nasa')
assert [x.identifier for x in r.iter_as_items()] == ['nasa']
assert r.iter_as_items().search == r
def test_download_destdir(tmpdir, nasa_item):
tmpdir.chdir()
with IaRequestsMock() as rsps:
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='new destdir')
dest = os.path.join(str(tmpdir), 'new destdir')
nasa_item.download(files='nasa_meta.xml', destdir=dest)
assert 'nasa' in os.listdir(dest)
with open(os.path.join(dest, 'nasa/nasa_meta.xml'), 'r') as fh:
assert fh.read() == 'new destdir'
def test_download_ignore_existing(tmpdir, nasa_item):
tmpdir.chdir()
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='test content')
nasa_item.download(files='nasa_meta.xml', ignore_existing=True)
rsps.add(responses.GET, DOWNLOAD_URL_RE, body='new test content')
nasa_item.download(files='nasa_meta.xml', ignore_existing=True)
with open('nasa/nasa_meta.xml', 'r') as fh:
assert fh.read() == 'test content'
def test_ia_list_non_existing(capsys):
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa', body='{}')
try:
ia_list.main(['list', 'nasa'], SESSION)
except SystemExit as exc:
assert exc.code == 1
out, err = capsys.readouterr()
assert out == ''
def test_upload_file_keys(nasa_item):
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.PUT, S3_URL_RE, adding_headers=EXPECTED_S3_HEADERS)
files = {'new_key.txt': NASA_METADATA_PATH, '222': NASA_METADATA_PATH}
_responses = nasa_item.upload(files, access_key='a', secret_key='b')
expected_urls = [
f'{PROTOCOL}//s3.us.archive.org/nasa/new_key.txt',
f'{PROTOCOL}//s3.us.archive.org/nasa/222',
]
for resp in _responses:
assert resp.request.url in expected_urls
def test_download_verbose(tmpdir, capsys, nasa_item):
tmpdir.chdir()
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.GET,
DOWNLOAD_URL_RE,
body='no dest dir',
adding_headers={'content-length': '100'})
nasa_item.download(files='nasa_meta.xml', verbose=True)
out, err = capsys.readouterr()
print(repr(err))
assert 'downloading nasa_meta.xml' in err
def test_ia_metadata_modify(capsys):
md_rsp = ('{"success":true,"task_id":447613301,'
'"log":"https://catalogd.archive.org/log/447613301"}')
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
rsps.add_metadata_mock('nasa', body=md_rsp, method=responses.POST)
rsps.add_metadata_mock('nasa')
valid_key = f'foo-{int(time())}'
ia_call(['ia', 'metadata', '--modify', f'{valid_key}:test_value', 'nasa'])
out, err = capsys.readouterr()
assert err == 'nasa - success: https://catalogd.archive.org/log/447613301\n'
def test_get_item_with_kwargs():
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add_metadata_mock('nasa')
item = get_item('nasa', http_adapter_kwargs={'max_retries': 13})
assert isinstance(item.session.adapters['{0}//'.format(PROTOCOL)].max_retries,
urllib3.Retry)
try:
get_item('nasa', request_kwargs={'timeout': .0000000000001})
except Exception as exc:
assert 'timed out' in str(exc)
def test_ia_metadata_exists(capsys):
with IaRequestsMock() as rsps:
rsps.add_metadata_mock('nasa')
ia_call(['ia', 'metadata', '--exists', 'nasa'])
out, err = capsys.readouterr()
assert out == 'nasa exists\n'
rsps.add_metadata_mock('nasa', '{}')
sys.argv = ['ia', 'metadata', '--exists', 'nasa']
ia_call(['ia', 'metadata', '--exists', 'nasa'], expected_exit_code=1)
out, err = capsys.readouterr()
assert err == 'nasa does not exist\n'
def test_download(tmpdir):
tmpdir.chdir()
with IaRequestsMock() as rsps:
rsps.add(responses.GET,
'{0}//archive.org/download/nasa/nasa_meta.xml'.format(PROTOCOL),
body='test content')
rsps.add_metadata_mock('nasa')
download('nasa', 'nasa_meta.xml')
p = os.path.join(str(tmpdir), 'nasa')
assert len(os.listdir(p)) == 1
assert load_file('nasa/nasa_meta.xml') == 'test content'
def test_download_dry_run(tmpdir, capsys, nasa_item):
tmpdir.chdir()
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.GET, DOWNLOAD_URL_RE,
body='no dest dir',
adding_headers={'content-length': '100'})
nasa_item.download(formats='Metadata', dry_run=True)
expected = set(['nasa_reviews.xml', 'nasa_meta.xml', 'nasa_files.xml'])
out, err = capsys.readouterr()
assert set([x.split('/')[-1] for x in out.split('\n') if x]) == expected
def test_upload_validate_identifier(session):
item = session.get_item('føø')
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.PUT, S3_URL_RE, adding_headers=EXPECTED_S3_HEADERS)
try:
item.upload(NASA_METADATA_PATH,
access_key='a',
secret_key='b',
validate_identifier=True)
assert False
except Exception as exc:
assert isinstance(exc, InvalidIdentifierException)
valid_item = session.get_item('foo')
with IaRequestsMock(assert_all_requests_are_fired=False) as rsps:
rsps.add(responses.PUT, S3_URL_RE, adding_headers=EXPECTED_S3_HEADERS)
valid_item.upload(NASA_METADATA_PATH,
access_key='a',
secret_key='b',
validate_identifier=True)
assert True
