def test_by_id(db, capsys): # capsys is a Pytest builtin fixture
from dlx.marc import Auth, Bib, BibSet
from xmldiff.main import diff_texts
control = '<collection><record><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DHL)1</subfield></datafield><datafield tag="191" ind1=" " ind2=" "><subfield code="a">TEST/1</subfield></datafield><datafield tag="245" ind1=" " ind2=" "><subfield code="a">title_1</subfield></datafield><datafield tag="700" ind1=" " ind2=" "><subfield code="a">name_1</subfield><subfield code="0">(DHLAUTH)1</subfield></datafield><datafield tag="980" ind1=" " ind2=" "><subfield code="a">BIB</subfield></datafield><datafield tag="FFT" ind1=" " ind2=" "><subfield code="a">https://mock_bucket.s3.amazonaws.com/1e50210a0202497fb79bc38b6ade6c34</subfield><subfield code="d">English</subfield><subfield code="n">TEST_1-EN.pdf</subfield></datafield></record></collection>'
dlx_dl.run(connect=db, source='test', type='bib', id='1', xml='STDOUT')
assert diff_texts(capsys.readouterr().out, control) == []
control = '<collection><record><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DHLAUTH)1</subfield></datafield><datafield tag="100" ind1=" " ind2=" "><subfield code="a">name_1</subfield></datafield><datafield tag="980" ind1=" " ind2=" "><subfield code="a">AUTHORITY</subfield></datafield><datafield tag="980" ind1=" " ind2=" "><subfield code="a">PERSONAL</subfield></datafield></record></collection>'
dlx_dl.run(connect=db, source='test', type='auth', id='1', xml='STDOUT')
assert diff_texts(capsys.readouterr().out, control) == []
# --ids
dlx_dl.run(connect=db, source='test', type='auth', ids=['1'], xml='STDOUT')
assert diff_texts(capsys.readouterr().out, control) == []
def test_modified_since_log(db, capsys):
from http.server import HTTPServer
from xmldiff.main import diff_texts
from dlx import DB
from dlx.marc import Bib
server = HTTPServer(('127.0.0.1', 9090), None)
responses.add(responses.POST, 'http://127.0.0.1:9090', body='test OK')
dlx_dl.API_URL = 'http://127.0.0.1:9090'
dlx_dl.run(connect=db,
source='test',
type='bib',
modified_within=100,
use_api=True,
api_key='x')
capsys.readouterr().out # clear stdout
Bib().set('999', 'a', 'new').commit()
dlx_dl.run(connect=db,
source='test',
type='bib',
modified_since_log=True,
use_api=True,
api_key='x')
entry = db['dummy']['dlx_dl_log'].find_one({'record_id': 3})
control = '<record><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DHL)3</subfield></datafield><datafield tag="980" ind1=" " ind2=" "><subfield code="a">BIB</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">new</subfield></datafield></record>'
assert diff_texts(entry['xml'], control) == []
def test_to_file(db, tmp_path):
from xmldiff.main import diff_texts
control = '<collection><record><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DHL)1</subfield></datafield><datafield tag="191" ind1=" " ind2=" "><subfield code="a">TEST/1</subfield></datafield><datafield tag="245" ind1=" " ind2=" "><subfield code="a">title_1</subfield></datafield><datafield tag="700" ind1=" " ind2=" "><subfield code="a">name_1</subfield><subfield code="0">(DHLAUTH)1</subfield></datafield><datafield tag="980" ind1=" " ind2=" "><subfield code="a">BIB</subfield></datafield><datafield tag="FFT" ind1=" " ind2=" "><subfield code="a">https://mock_bucket.s3.amazonaws.com/1e50210a0202497fb79bc38b6ade6c34</subfield><subfield code="d">English</subfield><subfield code="n">TEST_1-EN.pdf</subfield></datafield></record></collection>'
out = tmp_path / 'out.xml'
dlx_dl.run(connect=db, source='test', type='bib', id='1', xml=out)
assert diff_texts(out.read_text(), control) == []
def test_post_and_log(db, excel_export):
from http.server import HTTPServer
from xmldiff.main import diff_texts
server = HTTPServer(('127.0.0.1', 9090), None)
responses.add(responses.POST, 'http://127.0.0.1:9090', body='test OK')
dlx_dl.API_URL = 'http://127.0.0.1:9090'
dlx_dl.run(connect=db,
source='test',
type='bib',
modified_within=100,
use_api=True,
api_key='x')
entry = db['dummy']['dlx_dl_log'].find_one({'record_id': 1})
assert entry['record_id'] == 1
assert entry['response_code'] == 200
assert entry['response_text'] == 'test OK'
assert isinstance(entry['export_start'], datetime)
assert isinstance(entry['time'], datetime)
control = '<record><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DHL)1</subfield></datafield><datafield tag="191" ind1=" " ind2=" "><subfield code="a">TEST/1</subfield></datafield><datafield tag="245" ind1=" " ind2=" "><subfield code="a">title_1</subfield></datafield><datafield tag="700" ind1=" " ind2=" "><subfield code="a">name_1</subfield><subfield code="0">(DHLAUTH)1</subfield></datafield><datafield tag="980" ind1=" " ind2=" "><subfield code="a">BIB</subfield></datafield><datafield tag="FFT" ind1=" " ind2=" "><subfield code="a">https://mock_bucket.s3.amazonaws.com/1e50210a0202497fb79bc38b6ade6c34</subfield><subfield code="d">English</subfield><subfield code="n">TEST_1-EN.pdf</subfield></datafield></record>'
assert diff_texts(entry['xml'], control) == []
entry = db['dummy']['dlx_dl_log'].find_one({'source': 'test'})
assert isinstance(entry['export_start'], datetime)
entry = db['dummy']['dlx_dl_log'].find_one({
'source': 'test',
'export_end': {
'$exists': 1
}
})
assert entry['record_type'] == 'bib'
assert isinstance(entry['export_end'], datetime)
def test_multiple_test_cases_with_different_verdicts(self):
self.maxDiff = None
tc1 = TestCaseResult('tc1', 'a.b.tc1', times[0][0])
tc1.set_finished(times[0][2], Verdict.PASSED, None, '')
tc2 = TestCaseResult('tc2', 'a.b.tc2', times[1][0])
tc2.set_finished(times[1][2], Verdict.FAILED, AssertionError('Message'), 'stacktrace')
tc3 = TestCaseResult('tc3', 'a.c.tc3', times[2][0])
tc3.set_finished(
times[2][2], Verdict.SKIPPED, AssertionError('test case skipped'), 'stacktrace')
test_results = results([tc1, tc2, tc3])
self.assertFalse(
main.diff_texts(
writer.generate_junit_report(test_results).encode('utf-8'),
dedent(
f"""\
<testsuites disabled="0" errors="0" failures="1" tests="3" time="54.102">
\t<testsuite disabled="0" errors="0" failures="1" file="None" log="None" name="Name of Suite" skipped="1" tests="3" time="54.102" timestamp="{times[0][1]}" url="None">
\t\t<testcase classname="a.b" name="tc1" status="SUCCESSFUL" time="{times[0][4]}" timestamp="{times[0][1]}"/>
\t\t<testcase classname="a.b" name="tc2" status="FAILED" time="{times[1][4]}" timestamp="{times[1][1]}">
\t\t\t<failure message="Message" type="failure">stacktrace</failure>
\t\t</testcase>
\t\t<testcase classname="a.c" name="tc3" status="SUCCESSFUL" time="{times[2][4]}" timestamp="{times[2][1]}">
\t\t\t<skipped message="test case skipped" type="skipped">stacktrace</skipped>
\t\t</testcase>
\t</testsuite>
</testsuites>
""")))
def xml_tree_equal_to_xml_string(et, xml_s: str) -> bool:
xml_actual = tostring(et, encoding="unicode")
actions = diff_texts(xml_actual, xml_s)
if actions:
print(actions)
# No actions indicates that xmldiff thinks these two XML documents are equal.
return len(actions) == 0
def test_xml_encoding():
from dlx.marc import Bib
from xmldiff import main
control = '<record><datafield ind1=" " ind2=" " tag="245"><subfield code="a">Title with an é</subfield></datafield></record>'
bib = Bib().set('245', 'a', 'Title with an é')
assert main.diff_texts(bib.to_xml(), control) == []
def test_to_xml(db):
from dlx.marc import Bib
from xmldiff import main
control = '<record><controlfield tag="000">leader</controlfield><controlfield tag="008">controlfield</controlfield><datafield ind1=" " ind2=" " tag="245"><subfield code="a">This</subfield><subfield code="b">is the</subfield><subfield code="c">title</subfield></datafield><datafield ind1=" " ind2=" " tag="520"><subfield code="a">Description</subfield></datafield><datafield ind1=" " ind2=" " tag="520"><subfield code="a">Another description</subfield><subfield code="a">Repeated subfield</subfield></datafield><datafield ind1=" " ind2=" " tag="650"><subfield code="a">Header</subfield><subfield code="0">1</subfield></datafield><datafield ind1=" " ind2=" " tag="710"><subfield code="a">Another header</subfield><subfield code="0">2</subfield></datafield></record>'
bib = Bib.find_one({'_id': 1})
assert main.diff_texts(bib.to_xml(), control) == []
def compare_element_at_xpath(config: str, element: str, xpath: str,
context: dict) -> bool:
"""
Grab an xml fragment from the config given at xpath and compare it to this element
:param config: XML document string from which to pull the XML element to compare
:param element: element to check against
:param xpath: xpath to grab an xml fragment from the config for comparison
:param context: jinja context used to interpolate any variables that may be present in the template
:return: bool true if they match
"""
# render metadata will combine the xpath with the cherry_pick attribute to give us the full xpath
# to the element in question. It will also load the element from our source element or source file into the
# element attribute
if element == '' or element is None:
logger.warning('Element was blank for validate_xml test!')
return False
config_doc = elementTree.fromstring(config)
relative_xpath = xpath.replace('/config/', './')
config_element = config_doc.find(relative_xpath)
config_element_str = elementTree.tostring(config_element).strip()
diffs = xmldiff_main.diff_texts(config_element_str, element)
if len(diffs) == 0:
return True
return False
def test_test_case_with_owner(self):
self.maxDiff = None
tc = TestCaseResult('tc1', 'a.b.tc1', times[0][0])
tc.set_finished(
times[0][2],
Verdict.PASSED,
exception=None,
stacktrace=None,
owner=('Owner <*****@*****.**>'))
self.assertFalse(
main.diff_texts(
writer.generate_testng_report(results([tc])),
dedent(
"""\
<?xml version="1.0" encoding="utf-8"?>
<testng-results version="1.0">
<reporter-output/>
<suite duration-ms="18034" finished-at="2017-05-08T14:15:17Z" name="Name of Suite" started-at="2017-05-08T14:14:59Z">
<groups/>
<test duration-ms="18034" finished-at="2017-05-08T14:15:17Z" name="Name of Suite" started-at="2017-05-08T14:14:59Z">
<class name="a.b">
<test-method description="Test case owner: Owner <[email protected]> (Please contact the owner if you need assistance with trouble-shooting.)" duration-ms="18034" finished-at="2017-05-08T14:15:17Z" name="tc1" signature="a.b.tc1" started-at="2017-05-08T14:14:59Z" status="PASS"/>
</class>
</test>
</suite>
</testng-results>
""").encode('utf-8')))
def assert_xml_diff(actual, expected, msg=None):
# Only use xmldiff if it has been imported and both the xml messages
# contain data
if xml_diff and actual and expected:
diff = xml_diff.diff_texts(actual, expected)
assert len(diff) == 0, msg
else:
assert actual == expected, msg
def test_junit_xml_output(run_semgrep_in_tmp, snapshot):
actual_output = run_semgrep_in_tmp("rules/eqeq.yaml", output_format="junit-xml")
f = open(str(snapshot.snapshot_dir) + "/results.xml", "r")
expected_output = f.read()
f.close()
assert len(main.diff_texts(expected_output, actual_output)) == 0
def test_passed(self):
self.maxDiff = None
time_index = 1
self.assertFalse(
main.diff_texts(
writer.generate_testng_report(results([tc(Verdict.PASSED, time_index)])),
no_exception(time_index, 'PASS')))
def test_params_appended_to_test_case_name(self):
self.maxDiff = None
tc = TestCaseResult('tc1', 'a.b.tc1', times[0][0], params=['value1', 'value2'])
tc.set_finished(times[0][2], Verdict.PASSED, None, '[value1, value2]')
self.assertFalse(
main.diff_texts(
writer.generate_junit_report(results([tc])).encode('utf-8'),
no_exception(0, Verdict.PASSED, name_suffix='[value1, value2]')))
def test_passed(self):
self.maxDiff = None
time_index = 0
self.assertFalse(
main.diff_texts(
writer.generate_junit_report(results([tc(Verdict.PASSED,
time_index)])).encode('utf-8'),
no_exception(time_index, Verdict.PASSED)))
def test_api_diff_texts(self):
# diff_text can take bytes
with open(LEFT_FILE, "rb") as linfile:
with open(RIGHT_FILE, "rb") as rinfile:
left = linfile.read()
right = rinfile.read()
result1 = main.diff_texts(left, right)
# And unicode
result2 = main.diff_texts(left.decode("utf8"), right.decode("utf8"))
self.assertEqual(result1, result2)
with open(LEFT_FILE, "rb") as infile:
with open(RIGHT_FILE, "rb") as infile:
# Give something else, and it fails:
with self.assertRaises(ValueError):
main.diff_texts(infile, infile)
def test_by_list(db, tmp_path, capsys):
from xmldiff.main import diff_texts
ids = tmp_path / 'ids.txt'
ids.write_text('\n'.join([str(x) for x in (1, 2)]))
control = '<collection><record><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DHL)1</subfield></datafield><datafield tag="191" ind1=" " ind2=" "><subfield code="a">TEST/1</subfield></datafield><datafield tag="245" ind1=" " ind2=" "><subfield code="a">title_1</subfield></datafield><datafield tag="700" ind1=" " ind2=" "><subfield code="a">name_1</subfield><subfield code="0">(DHLAUTH)1</subfield></datafield><datafield tag="980" ind1=" " ind2=" "><subfield code="a">BIB</subfield></datafield><datafield tag="FFT" ind1=" " ind2=" "><subfield code="a">https://mock_bucket.s3.amazonaws.com/1e50210a0202497fb79bc38b6ade6c34</subfield><subfield code="d">English</subfield><subfield code="n">TEST_1-EN.pdf</subfield></datafield></record><record><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DHL)2</subfield></datafield><datafield tag="245" ind1=" " ind2=" "><subfield code="a">title_2</subfield></datafield><datafield tag="700" ind1=" " ind2=" "><subfield code="a">name_2</subfield><subfield code="0">(DHLAUTH)2</subfield></datafield><datafield tag="980" ind1=" " ind2=" "><subfield code="a">BIB</subfield></datafield></record></collection>'
dlx_dl.run(connect=db, source='test', type='bib', list=ids, xml='STDOUT')
assert diff_texts(capsys.readouterr().out, control) == []
def test_error_test_case_with_exception(self):
self.maxDiff = None
time_index = 0
self.assertFalse(
main.diff_texts(
writer.generate_junit_report(
results(
[tc(Verdict.ERROR, time_index, AssertionError('Message'),
'stacktrace')])).encode('utf-8'),
with_exception(time_index, Verdict.ERROR, 'stacktrace')))
def test_ignored_mapped_to_skip(self):
self.maxDiff = None
time_index = 0
self.assertFalse(
main.diff_texts(
writer.generate_junit_report(
results(
[tc(Verdict.IGNORED, time_index, AssertionError('Message'),
'stacktrace')])).encode('utf-8'),
with_exception(time_index, Verdict.IGNORED, 'stacktrace')))
def test_create_default_config(self):
'''Make sure default config lines up with actual.'''
config = configs.default()
path = 'mr_utils/test_data/tests/gadgetron/config/'
file = 'default.xml'
load_test_data(path, [file], do_return=False)
with open('%s/%s' % (path, file), 'r') as f:
truth = f.read()
res = len(main.diff_texts(truth.encode(), config.tostring().encode()))
self.assertTrue(res == 0)
def test_diff_patch(self):
here = os.path.split(__file__)[0]
lfile = os.path.join(here, "test_data", "all_actions.left.xml")
rfile = os.path.join(here, "test_data", "all_actions.right.xml")
with open(lfile) as f:
left = f.read()
with open(rfile) as f:
right = f.read()
diff = diff_texts(left, right, formatter=DiffFormatter(normalize=WS_NONE))
result = patch_text(diff, left)
compare_elements(etree.fromstring(result), etree.fromstring(right))
def test_pending_mapped_to_fail(self):
self.maxDiff = None
time_index = 2
self.assertFalse(
main.diff_texts(
writer.generate_testng_report(
results(
[
tc(
Verdict.PENDING, time_index, AssertionError('assert failed'),
'stacktrace')
])), with_exception(time_index, 'FAIL', 'stacktrace')))
def test_ignored_mapped_to_skip(self):
self.maxDiff = None
time_index = 2
self.assertFalse(
main.diff_texts(
writer.generate_testng_report(
results(
[
tc(
Verdict.IGNORED, time_index, AssertionError('assert failed'),
'stacktrace')
])), with_exception(time_index, 'SKIP', 'stacktrace')))
def test_failed_test_case_with_exception(self):
self.maxDiff = None
time_index = 1
self.assertFalse(
main.diff_texts(
writer.generate_testng_report(
results(
[
tc(
Verdict.FAILED, time_index, AssertionError('assert failed'),
'stacktrace')
])), with_exception(time_index, 'FAIL', 'stacktrace')))
def compare(self, old: str, new: str):
old, new = self.preprocess(old, new)
old, new = get_xml(old), get_xml(new)
diffs = xml.diff_texts(old,
new,
diff_options={
'F': 0.5,
'ratio_mode': 'accurate'
})
diff = xml.diff_texts(
old,
new,
formatter=formatting.XMLFormatter(normalize=formatting.WS_BOTH),
diff_options={
'F': 0.5,
'ratio_mode': 'accurate'
})
diff = normalize_html(diff)
self.set_style(diff)
return diff.prettify()
def test_module_xml(orb_course):
"""Ensure the module.xml content is built as expected
Test against an existing XML file by reading into memory
"""
oppia_exporter = orb_course.oppia_exporter() # type: OppiaExport
expected_file_path = os.path.join(os.path.dirname(__file__), "expected_module.xml")
with open(expected_file_path, "r") as expected_file:
# expected_xml = ET.fromstring(expected_file.read())
diff = differ.diff_texts(
expected_file.read(),
oppia_exporter.module_xml(oppia_exporter.module_context()),
)
assert not diff
def test_paragraph_conversion():
paragraph_base = f"{os.path.dirname(os.path.realpath(__file__))}/data/paragraph_"
input_path = f"{paragraph_base}input.txt"
target_path = f"{paragraph_base}target.xml"
with open(input_path, "r") as f:
paragraph = f.read()
with open(target_path, "rb") as f:
target = f.read()
actual_out = FrameAnnotatorGenerator.convert(paragraph).encode("UTF-8")
actions_to_fix_differences = main.diff_texts(actual_out, target)
# Assert that only changes that need to happen are to the timestamp
assert (len(actions_to_fix_differences) == len([
action for action in actions_to_fix_differences
if action.name == "cDate"
]))
def test_module_xml(orb_course):
"""Ensure the module.xml content is built as expected
Test against an existing XML file by reading into memory
"""
oppia_exporter = orb_course.oppia_exporter() # type: OppiaExport
expected_file_path = os.path.join(os.path.dirname(__file__),
"expected_module.xml")
with open(expected_file_path, "r") as expected_file:
# expected_xml = ET.fromstring(expected_file.read())
diff = differ.diff_texts(
expected_file.read(),
oppia_exporter.module_xml(oppia_exporter.module_context()),
)
assert not diff
def test_run_verdict_mapped_to_test_case(self):
self.maxDiff = None
self.assertFalse(
main.diff_texts(
writer.generate_junit_report(
results([tc(Verdict.PASSED, 0)], run_verdict=Verdict.FAILED)).encode('utf-8'),
dedent(
f"""\
<testsuites disabled="0" errors="0" failures="1" tests="2" time="18.034">
\t<testsuite disabled="0" errors="0" failures="1" file="None" log="None" name="Name of Suite" skipped="0" tests="2" time="18.034" timestamp="{times[0][1]}" url="None">
\t\t<testcase classname="a.b" name="tc1" status="SUCCESSFUL" time="{times[0][4]}" timestamp="{times[0][1]}"/>
\t\t<testcase classname="Name of Suite" name="Name of Suite" status="FAILED" timestamp="{times[0][1]}">
\t\t\t<failure message="Message" type="failure"/>
\t\t</testcase>
\t</testsuite>
</testsuites>
""")))
def compare(esdls):
with self.flask_app.app_context():
esh = get_handler()
es_id1 = esdls['esdl1']
es_id2 = esdls['esdl2']
es1_str = esh.to_string(
es_id1).encode() # convert string to bytes
es2_str = esh.to_string(
es_id2).encode() # convert string to bytes
logger.info("Comparing EnergySystems with id {} and {}".format(
es_id1, es_id2))
results = main.diff_texts(es1_str, es2_str)
emit('esdl_compare_window', results, namespace='/esdl')
def test_run_verdict_mapped_to_test_case(self):
self.maxDiff = None
self.assertFalse(
main.diff_texts(
writer.generate_testng_report(
results([tc(Verdict.PASSED, 0)], run_verdict=Verdict.FAILED)),
dedent(
"""\
<?xml version="1.0" encoding="utf-8"?>
<testng-results version="1.0">
<reporter-output/>
<suite duration-ms="18034" finished-at="2017-05-08T14:15:17Z" name="Name of Suite" started-at="2017-05-08T14:14:59Z">
<groups/>
<test duration-ms="18034" finished-at="2017-05-08T14:15:17Z" name="Name of Suite" started-at="2017-05-08T14:14:59Z">
<class name="a.b">
<test-method duration-ms="18034" finished-at="2017-05-08T14:15:17Z" name="tc1" signature="a.b.tc1" started-at="2017-05-08T14:14:59Z" status="PASS"/>
</class>
<class name="Name of Suite">
<test-method duration-ms="18034" finished-at="2017-05-08T14:15:17Z" name="Name of Suite" signature="Name of Suite" started-at="2017-05-08T14:14:59Z" status="FAIL">
<exception class="str">
<message>
<![CDATA[A
multiline
error
message
.]]> \n\
\n\
</message>
<full-stacktrace>
<![CDATA[str: A
multiline
error
message
.
]]> \n\
\n\
</full-stacktrace>
</exception>
<reporter-output/>
</test-method>
</class>
</test>
</suite>
</testng-results>
""").encode('utf-8')))
