def test_pydict_zero_rows(self):
with tempfile_context() as path:
# ensure at least 1 row group
parquet.write(
path,
pyarrow.table({
"A":
pyarrow.array([], type=pyarrow.string()),
"B":
pyarrow.DictionaryArray.from_arrays(
pyarrow.array([], type=pyarrow.int32()),
pyarrow.array([], type=pyarrow.string()),
),
"C":
pyarrow.array([], type=pyarrow.timestamp("ns")),
"D":
pyarrow.array([], type=pyarrow.float64()),
}),
)
self.assertEqual(
parquet.read_pydict(path, range(4), range(0)),
{
"A": [],
"B": [],
"C": [],
"D": []
},
)
def _test_read_write_table(self, table, expected=None):
table = arrow_table(table).table
if expected is None:
expected = table
else:
expected = arrow_table(expected).table
parquet.write(self.temp_path, table)
result = parquet.read(self.temp_path)
assert_arrow_table_equals(result, table)
def test_parquet_same_data_different_bytes(self):
parquet.write(self.old_path, arrow_table({"A": ["a"]}).table)
parquet.write(
self.new_path,
arrow_table({
"A": pyarrow.array(["a"]).dictionary_encode()
}).table,
)
self.assertTrue(
are_fetch_results_equal(FetchResult(self.old_path),
FetchResult(self.new_path)))
def cache_render_result(workflow: Workflow, wf_module: WfModule, delta_id: int,
result: RenderResult) -> None:
"""
Save `result` for later viewing.
Raise AssertionError if `delta_id` is not what we expect.
Since this alters data, be sure to call it within a lock:
with workflow.cooperative_lock():
wf_module.refresh_from_db() # may change delta_id
cache_render_result(workflow, wf_module, delta_id, result)
"""
assert delta_id == wf_module.last_relevant_delta_id
assert result is not None
json_bytes = json_encode(result.json).encode("utf-8")
if not result.table.metadata.columns:
if result.errors:
status = "error"
else:
status = "unreachable"
else:
status = "ok"
wf_module.cached_render_result_delta_id = delta_id
wf_module.cached_render_result_errors = result.errors
wf_module.cached_render_result_error = "" # DELETEME
wf_module.cached_render_result_quick_fixes = [] # DELETEME
wf_module.cached_render_result_status = status
wf_module.cached_render_result_json = json_bytes
wf_module.cached_render_result_columns = result.table.metadata.columns
wf_module.cached_render_result_nrows = result.table.metadata.n_rows
# Now we get to the part where things can end up inconsistent. Try to
# err on the side of not-caching when that happens.
delete_parquet_files_for_wf_module(
workflow.id, wf_module.id) # makes old cache inconsistent
wf_module.save(
update_fields=WF_MODULE_FIELDS) # makes new cache inconsistent
if result.table.metadata.columns: # only write non-zero-column tables
with tempfile_context() as parquet_path:
parquet.write(parquet_path, result.table.table)
minio.fput_file(BUCKET,
parquet_key(workflow.id, wf_module.id, delta_id),
parquet_path) # makes new cache consistent
def test_slice_zero_rows(self):
with tempfile_context() as path:
# ensure at least 1 row group
parquet.write(
path,
pa.table({
"A":
pa.array([], pa.string()),
"B":
pa.DictionaryArray.from_arrays(pa.array([], pa.int32()),
pa.array([], pa.string())),
"C":
pa.array([], pa.timestamp("ns")),
"D":
pa.array([], pa.float64()),
}),
)
self.assertEqual(
parquet.read_slice_as_text(path, "csv", range(4), range(0)),
"A,B,C,D")
self.assertEqual(
parquet.read_slice_as_text(path, "json", range(4), range(0)),
"[]")
def fetch_arrow(
params: Dict[str, Any],
secrets: Dict[str, Any],
last_fetch_result: Optional[types.FetchResult],
input_table_parquet_path: Optional[Path],
output_path: Path,
) -> types.FetchResult:
"""
Render using `cjwkernel.types` data types.
The result will be encoded as a Parquet file.
Module authors are encouraged to replace this function, because the
`fetch()` signature deals in dataframes instead of in raw data.
"""
pandas_result: Union[ptypes.ProcessResult,
types.FetchResult] = fetch_pandas(
params=_arrow_param_to_pandas_param(params),
secrets=secrets,
last_fetch_result=last_fetch_result,
input_table_parquet_path=input_table_parquet_path,
output_path=output_path,
)
if isinstance(pandas_result, ptypes.ProcessResult):
pandas_result.truncate_in_place_if_too_big()
# ProcessResult => FetchResult isn't a thing; but we can hack it using
# ProcessResult => RenderResult => FetchResult.
with tempfile_context(suffix=".arrow") as arrow_path:
hacky_result = pandas_result.to_arrow(arrow_path)
if hacky_result.table.path:
parquet.write(output_path, hacky_result.table.table)
else:
output_path.write_bytes(b"")
return types.FetchResult(output_path, hacky_result.errors)
else: # it's already a types.FetchResult
return pandas_result
def test_parquet_vs_non_parquet(self):
parquet.write(self.old_path, arrow_table({"A": ["a"]}).table)
self.new_path.write_bytes(b"12345")
self.assertFalse(
are_fetch_results_equal(FetchResult(self.old_path),
FetchResult(self.new_path)))
def test_parquet_different(self):
parquet.write(self.old_path, arrow_table({"A": [1]}).table)
parquet.write(self.new_path, arrow_table({"A": [2]}).table)
self.assertFalse(
are_fetch_results_equal(FetchResult(self.old_path),
FetchResult(self.new_path)))
