def _suite_edit_workflow(
context: DataContext,
expectation_suite_name: str,
profile: bool,
usage_event: str,
interactive: bool,
no_jupyter: bool,
create_if_not_exist: Optional[bool] = False,
datasource_name: Optional[str] = None,
batch_request: Optional[Union[str, Dict[str, Union[str, int,
Dict[str,
Any]]]]] = None,
additional_batch_request_args: Optional[Dict[str,
Union[str, int,
Dict[str,
Any]]]] = None,
suppress_usage_message: Optional[bool] = False,
assume_yes: Optional[bool] = False,
):
# suppress_usage_message flag is for the situation where _suite_edit_workflow is called by _suite_new_workflow().
# when called by _suite_new_workflow(), the flag will be set to True, otherwise it will default to False
if suppress_usage_message:
usage_event = None
suite: ExpectationSuite = toolkit.load_expectation_suite(
data_context=context,
expectation_suite_name=expectation_suite_name,
usage_event=usage_event,
create_if_not_exist=create_if_not_exist,
)
try:
if interactive or profile:
batch_request_from_citation_is_up_to_date: bool = True
batch_request_from_citation: Optional[Union[str, Dict[str, Union[
str, Dict[str,
Any]]]]] = toolkit.get_batch_request_from_citations(
expectation_suite=suite)
if batch_request is not None and isinstance(batch_request, str):
batch_request = toolkit.get_batch_request_from_json_file(
batch_request_json_file_path=batch_request,
data_context=context,
usage_event=usage_event,
suppress_usage_message=suppress_usage_message,
)
if batch_request != batch_request_from_citation:
batch_request_from_citation_is_up_to_date = False
if not (batch_request and isinstance(batch_request, dict)
and BatchRequest(**batch_request)):
if (batch_request_from_citation
and isinstance(batch_request_from_citation, dict)
and BatchRequest(**batch_request_from_citation)):
batch_request = copy.deepcopy(batch_request_from_citation)
else:
batch_request = toolkit.get_batch_request_using_datasource_name(
data_context=context,
datasource_name=datasource_name,
usage_event=usage_event,
suppress_usage_message=False,
additional_batch_request_args=
additional_batch_request_args,
)
if batch_request != batch_request_from_citation:
batch_request_from_citation_is_up_to_date = False
if not batch_request_from_citation_is_up_to_date:
toolkit.add_citation_with_batch_request(
data_context=context,
expectation_suite=suite,
batch_request=batch_request,
)
notebook_name: str = "edit_{}.ipynb".format(expectation_suite_name)
notebook_path: str = _get_notebook_path(context, notebook_name)
if profile:
if not assume_yes:
toolkit.prompt_profile_to_create_a_suite(
data_context=context,
expectation_suite_name=expectation_suite_name)
renderer: SuiteProfileNotebookRenderer = SuiteProfileNotebookRenderer(
context=context,
expectation_suite_name=expectation_suite_name,
batch_request=batch_request,
)
renderer.render_to_disk(notebook_file_path=notebook_path)
else:
SuiteEditNotebookRenderer.from_data_context(
data_context=context).render_to_disk(
suite=suite,
notebook_file_path=notebook_path,
batch_request=batch_request,
)
if no_jupyter:
cli_message(
string=
f"To continue editing this suite, run <green>jupyter notebook {notebook_path}</green>"
)
else:
cli_message(
string=
"""<green>Opening a notebook for you now to edit your expectation suite!
If you wish to avoid this you can add the `--no-jupyter` flag.</green>\n\n""")
payload: dict = edit_expectation_suite_usage_statistics(
data_context=context,
expectation_suite_name=suite.expectation_suite_name)
if not suppress_usage_message:
toolkit.send_usage_message(
data_context=context,
event=usage_event,
event_payload=payload,
success=True,
)
if not no_jupyter:
toolkit.launch_jupyter_notebook(notebook_path=notebook_path)
except (
ge_exceptions.DataContextError,
ge_exceptions.ProfilerError,
ValueError,
OSError,
SQLAlchemyError,
) as e:
cli_message(string="<red>{}</red>".format(e))
if not suppress_usage_message:
toolkit.send_usage_message(data_context=context,
event=usage_event,
success=False)
sys.exit(1)
except Exception as e:
if not suppress_usage_message:
toolkit.send_usage_message(data_context=context,
event=usage_event,
success=False)
raise e
def _suite_edit(suite, datasource, directory, jupyter, batch_kwargs, usage_event):
batch_kwargs_json = batch_kwargs
batch_kwargs = None
context = load_data_context_with_error_handling(directory)
try:
suite = load_expectation_suite(context, suite)
citations = suite.get_citations(require_batch_kwargs=True)
if batch_kwargs_json:
try:
batch_kwargs = json.loads(batch_kwargs_json)
if datasource:
batch_kwargs["datasource"] = datasource
_batch = toolkit.load_batch(context, suite, batch_kwargs)
except json_parse_exception as je:
cli_message(
"<red>Please check that your batch_kwargs are valid JSON.\n{}</red>".format(
je
)
)
send_usage_message(
data_context=context, event=usage_event, success=False
)
sys.exit(1)
except ge_exceptions.DataContextError:
cli_message(
"<red>Please check that your batch_kwargs are able to load a batch.</red>"
)
send_usage_message(
data_context=context, event=usage_event, success=False
)
sys.exit(1)
except ValueError as ve:
cli_message(
"<red>Please check that your batch_kwargs are able to load a batch.\n{}</red>".format(
ve
)
)
send_usage_message(
data_context=context, event=usage_event, success=False
)
sys.exit(1)
elif citations:
citation = citations[-1]
batch_kwargs = citation.get("batch_kwargs")
if not batch_kwargs:
cli_message(
"""
A batch of data is required to edit the suite - let's help you to specify it."""
)
additional_batch_kwargs = None
try:
data_source = select_datasource(context, datasource_name=datasource)
except ValueError as ve:
cli_message("<red>{}</red>".format(ve))
send_usage_message(
data_context=context, event=usage_event, success=False
)
sys.exit(1)
if not data_source:
cli_message("<red>No datasources found in the context.</red>")
send_usage_message(
data_context=context, event=usage_event, success=False
)
sys.exit(1)
if batch_kwargs is None:
(
datasource_name,
batch_kwargs_generator,
data_asset,
batch_kwargs,
) = get_batch_kwargs(context, datasource_name=data_source.name,
additional_batch_kwargs=additional_batch_kwargs)
notebook_name = "edit_{}.ipynb".format(suite.expectation_suite_name)
notebook_path = _get_notebook_path(context, notebook_name)
SuiteEditNotebookRenderer().render_to_disk(suite, notebook_path, batch_kwargs)
if not jupyter:
cli_message(
f"To continue editing this suite, run <green>jupyter notebook {notebook_path}</green>"
)
payload = edit_expectation_suite_usage_statistics(
data_context=context, expectation_suite_name=suite.expectation_suite_name
)
send_usage_message(
data_context=context, event=usage_event, event_payload=payload, success=True
)
if jupyter:
toolkit.launch_jupyter_notebook(notebook_path)
except Exception as e:
send_usage_message(data_context=context, event=usage_event, success=False)
raise e
def _suite_edit(suite, datasource, directory, jupyter, batch_kwargs):
batch_kwargs_json = batch_kwargs
batch_kwargs = None
try:
context = DataContext(directory)
except ge_exceptions.ConfigNotFoundError as err:
cli_message("<red>{}</red>".format(err.message))
return
try:
suite = load_expectation_suite(context, suite)
citations = suite.get_citations(sort=True, require_batch_kwargs=True)
if batch_kwargs_json:
try:
batch_kwargs = json.loads(batch_kwargs_json)
if datasource:
batch_kwargs["datasource"] = datasource
_batch = context.get_batch(batch_kwargs, suite.expectation_suite_name)
assert isinstance(_batch, DataAsset)
except json_parse_exception as je:
cli_message(
"<red>Please check that your batch_kwargs are valid JSON.\n{}</red>".format(
je
)
)
send_usage_message(
data_context=context,
event="cli.suite.edit",
success=False
)
sys.exit(1)
except ge_exceptions.DataContextError:
cli_message(
"<red>Please check that your batch_kwargs are able to load a batch.</red>"
)
send_usage_message(
data_context=context,
event="cli.suite.edit",
success=False
)
sys.exit(1)
except ValueError as ve:
cli_message(
"<red>Please check that your batch_kwargs are able to load a batch.\n{}</red>".format(
ve
)
)
send_usage_message(
data_context=context,
event="cli.suite.edit",
success=False
)
sys.exit(1)
elif citations:
citation = citations[-1]
batch_kwargs = citation.get("batch_kwargs")
if not batch_kwargs:
cli_message(
"""
A batch of data is required to edit the suite - let's help you to specify it."""
)
additional_batch_kwargs = None
try:
data_source = select_datasource(context, datasource_name=datasource)
except ValueError as ve:
cli_message("<red>{}</red>".format(ve))
send_usage_message(
data_context=context,
event="cli.suite.edit",
success=False
)
sys.exit(1)
if not data_source:
cli_message("<red>No datasources found in the context.</red>")
send_usage_message(
data_context=context,
event="cli.suite.edit",
success=False
)
sys.exit(1)
if batch_kwargs is None:
(
datasource_name,
batch_kwargs_generator,
data_asset,
batch_kwargs,
) = get_batch_kwargs(
context,
datasource_name=data_source.name,
batch_kwargs_generator_name=None,
generator_asset=None,
additional_batch_kwargs=additional_batch_kwargs,
)
notebook_name = "{}.ipynb".format(suite.expectation_suite_name)
notebook_path = os.path.join(
context.root_directory, context.GE_EDIT_NOTEBOOK_DIR, notebook_name
)
NotebookRenderer().render_to_disk(suite, notebook_path, batch_kwargs)
if not jupyter:
cli_message("To continue editing this suite, run <green>jupyter "
f"notebook {notebook_path}</green>")
payload = edit_expectation_suite_usage_statistics(
data_context=context,
expectation_suite_name=suite.expectation_suite_name
)
send_usage_message(
data_context=context,
event="cli.suite.edit",
event_payload=payload,
success=True
)
if jupyter:
subprocess.call(["jupyter", "notebook", notebook_path])
except Exception as e:
send_usage_message(
data_context=context,
event="cli.suite.edit",
success=False
)
raise e
