def test_documentation():
platform = "urn:li:dataPlatform:kafka"
dataset_name = ("test-timeline-sample-kafka")
env = "PROD"
dataset_urn = f"urn:li:dataset:({platform},{dataset_name},{env})"
put(dataset_urn, "institutionalMemory",
"test_resources/timeline/newdocumentation.json")
put(dataset_urn, "institutionalMemory",
"test_resources/timeline/newdocumentationv2.json")
put(dataset_urn, "institutionalMemory",
"test_resources/timeline/newdocumentationv3.json")
res_data = timeline_cli.get_timeline(dataset_urn, ["DOCUMENTATION"], None,
None, False)
delete_cli.delete_one_urn_cmd(dataset_urn, False, False, "dataset", None,
None)
assert res_data
assert len(res_data) == 3
assert res_data[0]["semVerChange"] == "MINOR"
assert len(res_data[0]["changeEvents"]) == 1
assert res_data[1]["semVerChange"] == "MINOR"
assert len(res_data[1]["changeEvents"]) == 1
assert res_data[2]["semVerChange"] == "MINOR"
assert len(res_data[2]["changeEvents"]) == 3
assert res_data[2]["semVer"] == "0.2.0-computed"
def test_glossary():
platform = "urn:li:dataPlatform:kafka"
dataset_name = ("test-timeline-sample-kafka")
env = "PROD"
dataset_urn = f"urn:li:dataset:({platform},{dataset_name},{env})"
put(dataset_urn, "glossaryTerms",
"test_resources/timeline/newglossary.json")
put(dataset_urn, "glossaryTerms",
"test_resources/timeline/newglossaryv2.json")
put(dataset_urn, "glossaryTerms",
"test_resources/timeline/newglossaryv3.json")
res_data = timeline_cli.get_timeline(dataset_urn, ["GLOSSARY_TERM"], None,
None, False)
delete_cli.delete_one_urn_cmd(dataset_urn, False, False, "dataset", None,
None)
assert res_data
assert len(res_data) == 3
assert res_data[0]["semVerChange"] == "MINOR"
assert len(res_data[0]["changeEvents"]) == 1
assert res_data[1]["semVerChange"] == "MINOR"
assert len(res_data[1]["changeEvents"]) == 1
assert res_data[2]["semVerChange"] == "MINOR"
assert len(res_data[2]["changeEvents"]) == 2
assert res_data[2]["semVer"] == "0.2.0-computed"
def test_all():
platform = "urn:li:dataPlatform:kafka"
dataset_name = ("test-timeline-sample-kafka")
env = "PROD"
dataset_urn = f"urn:li:dataset:({platform},{dataset_name},{env})"
ingest_file_via_rest("tests/timeline/timeline_test_data.json")
ingest_file_via_rest("tests/timeline/timeline_test_datav2.json")
ingest_file_via_rest("tests/timeline/timeline_test_datav3.json")
res_data = timeline_cli.get_timeline(dataset_urn, [
"TAG", "DOCUMENTATION", "TECHNICAL_SCHEMA", "GLOSSARY_TERM",
"OWNERSHIP"
], None, None, False)
delete_cli.delete_one_urn_cmd(dataset_urn, False, False, "dataset", None,
None)
assert res_data
assert len(res_data) == 3
assert res_data[0]["semVerChange"] == "MINOR"
assert len(res_data[0]["changeEvents"]) == 10
assert res_data[1]["semVerChange"] == "MAJOR"
assert len(res_data[1]["changeEvents"]) == 9
assert res_data[2]["semVerChange"] == "MAJOR"
assert len(res_data[2]["changeEvents"]) == 7
assert res_data[2]["semVer"] == "2.0.0-computed"
def test_schema():
platform = "urn:li:dataPlatform:kafka"
dataset_name = ("test-timeline-sample-kafka")
env = "PROD"
dataset_urn = f"urn:li:dataset:({platform},{dataset_name},{env})"
put(dataset_urn, "schemaMetadata",
"test_resources/timeline/newschema.json")
put(dataset_urn, "schemaMetadata",
"test_resources/timeline/newschemav2.json")
put(dataset_urn, "schemaMetadata",
"test_resources/timeline/newschemav3.json")
res_data = timeline_cli.get_timeline(dataset_urn, ["TECHNICAL_SCHEMA"],
None, None, False)
delete_cli.delete_one_urn_cmd(dataset_urn, False, False, "dataset", None,
None)
assert res_data
assert len(res_data) == 3
assert res_data[0]["semVerChange"] == "MINOR"
assert len(res_data[0]["changeEvents"]) == 6
assert res_data[1]["semVerChange"] == "MAJOR"
assert len(res_data[1]["changeEvents"]) == 2
assert res_data[2]["semVerChange"] == "MAJOR"
assert len(res_data[2]["changeEvents"]) == 2
assert res_data[2]["semVer"] == "2.0.0-computed"
