support partitioning output parquet by namespace.
This commit is contained in:
@@ -199,6 +199,19 @@ def test_collapse_user():
|
||||
baseline = pd.read_table(tester.baseline_file)
|
||||
assert_frame_equal(test, baseline, check_like=True)
|
||||
|
||||
def test_partition_namespaces():
|
||||
tester = WikiqTester(SAILORMOON, "collapse-user", in_compression="7z", out_format='parquet', baseline_format='parquet')
|
||||
|
||||
try:
|
||||
tester.call_wikiq("--collapse-user", "--fandom-2020", "--partition-namespaces")
|
||||
except subprocess.CalledProcessError as exc:
|
||||
pytest.fail(exc.stderr.decode("utf8"))
|
||||
|
||||
test = pd.read_parquet(os.path.join(tester.output,"namespace=10/sailormoon.parquet"))
|
||||
baseline = pd.read_parquet(tester.baseline_file)
|
||||
assert_frame_equal(test, baseline, check_like=True)
|
||||
|
||||
|
||||
def test_pwr_wikidiff2():
|
||||
tester = WikiqTester(SAILORMOON, "persistence_wikidiff2", in_compression="7z")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user