def checkpoint_new(checkpoint, suite, directory, datasource): """Create a new checkpoint for easy deployments. (Experimental)""" suite_name = suite usage_event = "cli.checkpoint.new" context = toolkit.load_data_context_with_error_handling(directory) _verify_checkpoint_does_not_exist(context, checkpoint, usage_event) suite: ExpectationSuite = toolkit.load_expectation_suite( context, suite_name, usage_event ) datasource = toolkit.select_datasource(context, datasource_name=datasource) if datasource is None: toolkit.send_usage_message(context, usage_event, success=False) sys.exit(1) _, _, _, batch_kwargs = toolkit.get_batch_kwargs(context, datasource.name) _ = context.add_checkpoint( name=checkpoint, **{ "class_name": "LegacyCheckpoint", "batches": [ { "batch_kwargs": dict(batch_kwargs), "expectation_suite_names": [suite.expectation_suite_name], } ], }, ) cli_message( f"""<green>A Checkpoint named `{checkpoint}` was added to your project!</green> - To run this Checkpoint, run `great_expectations checkpoint run {checkpoint}`""" ) toolkit.send_usage_message(context, usage_event, success=True)
def checkpoint_new(checkpoint, suite, directory, datasource, legacy): """Create a new checkpoint for easy deployments. (Experimental)""" if legacy: suite_name = suite usage_event = "cli.checkpoint.new" context = toolkit.load_data_context_with_error_handling(directory) ge_config_version = context.get_config().config_version if ge_config_version >= 3: cli_message( f"""<red>The `checkpoint new` CLI command is not yet implemented for Great Expectations config versions >= 3.</red>""" ) toolkit.send_usage_message(context, usage_event, success=False) sys.exit(1) _verify_checkpoint_does_not_exist(context, checkpoint, usage_event) suite: ExpectationSuite = toolkit.load_expectation_suite( context, suite_name, usage_event) datasource = toolkit.select_datasource(context, datasource_name=datasource) if datasource is None: toolkit.send_usage_message(context, usage_event, success=False) sys.exit(1) _, _, _, batch_kwargs = toolkit.get_batch_kwargs( context, datasource.name) _ = context.add_checkpoint( name=checkpoint, **{ "class_name": "LegacyCheckpoint", "validation_operator_name": "action_list_operator", "batches": [{ "batch_kwargs": dict(batch_kwargs), "expectation_suite_names": [suite.expectation_suite_name], }], }, ) cli_message( f"""<green>A checkpoint named `{checkpoint}` was added to your project!</green> - To run this checkpoint run `great_expectations checkpoint run {checkpoint}`""" ) toolkit.send_usage_message(context, usage_event, success=True) # TODO: <Rob>Rob</Rob> Add flow for new style checkpoints else: pass
def validation_operator_run(name, run_name, validation_config_file, suite, directory): # Note though the long lines here aren't pythonic, they look best if Click does the line wraps. """ Run a validation operator against some data. There are two modes to run this command: 1. Interactive (good for development): Specify the name of the validation operator using the --name argument and the name of the expectation suite using the --suite argument. The cli will help you specify the batch of data that you want to validate interactively. 2. Non-interactive (good for production): Use the `--validation_config_file` argument to specify the path of the validation configuration JSON file. This file can be used to instruct a validation operator to validate multiple batches of data and use multiple expectation suites to validate each batch. Learn how to create a validation config file here: https://great-expectations.readthedocs.io/en/latest/command_line.html#great-expectations-validation-operator-run-validation-config-file-validation-config-file-path This command exits with 0 if the validation operator ran and the "success" attribute in its return object is True. Otherwise, the command exits with 1. To learn more about validation operators, go here: https://great-expectations.readthedocs.io/en/latest/features/validation.html#validation-operators """ try: context = DataContext(directory) except ge_exceptions.ConfigNotFoundError as err: cli_message(f"Failed to process <red>{err.message}</red>") sys.exit(1) try: if validation_config_file is not None: try: with open(validation_config_file) as f: validation_config = json.load(f) except (OSError, json_parse_exception) as e: cli_message( f"Failed to process the --validation_config_file argument: <red>{e}</red>" ) toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=False, ) sys.exit(1) validation_config_error_message = _validate_valdiation_config( validation_config ) if validation_config_error_message is not None: cli_message( "<red>The validation config in {:s} is misconfigured: {:s}</red>".format( validation_config_file, validation_config_error_message ) ) toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=False, ) sys.exit(1) else: if suite is None: cli_message( """ Please use --suite argument to specify the name of the expectation suite. Call `great_expectation suite list` command to list the expectation suites in your project. """ ) toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=False, ) sys.exit(0) suite = toolkit.load_expectation_suite( context, suite, "cli.validation_operator.run" ) if name is None: cli_message( """ Please use --name argument to specify the name of the validation operator. Call `great_expectation validation-operator list` command to list the operators in your project. """ ) toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=False, ) sys.exit(1) else: if name not in context.list_validation_operator_names(): cli_message( f""" Could not find a validation operator {name}. Call `great_expectation validation-operator list` command to list the operators in your project. """ ) toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=False, ) sys.exit(1) batch_kwargs = None cli_message( """ Let us help you specify the batch of data your want the validation operator to validate.""" ) try: data_source = toolkit.select_datasource(context) except ValueError as ve: cli_message(f"<red>{ve}</red>") toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=False, ) sys.exit(1) if not data_source: cli_message("<red>No datasources found in the context.</red>") toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", 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, data_asset_name=None, additional_batch_kwargs=None, ) validation_config = { "validation_operator_name": name, "batches": [ { "batch_kwargs": batch_kwargs, "expectation_suite_names": [suite.expectation_suite_name], } ], } try: validation_operator_name = validation_config["validation_operator_name"] batches_to_validate = [] for entry in validation_config["batches"]: for expectation_suite_name in entry["expectation_suite_names"]: batch = context.get_batch( entry["batch_kwargs"], expectation_suite_name ) batches_to_validate.append(batch) if run_name is None: run_name = datetime.datetime.now(datetime.timezone.utc).strftime( "%Y%m%dT%H%M%S.%fZ" ) run_id = RunIdentifier(run_name=run_name) if suite is None: results = context.run_validation_operator( validation_operator_name, assets_to_validate=batches_to_validate, run_id=run_id, ) else: if suite.evaluation_parameters is None: results = context.run_validation_operator( validation_operator_name, assets_to_validate=batches_to_validate, run_id=run_id, ) else: results = context.run_validation_operator( validation_operator_name, assets_to_validate=batches_to_validate, run_id=run_id, evaluation_parameters=suite.evaluation_parameters, ) except (ge_exceptions.DataContextError, OSError, SQLAlchemyError) as e: cli_message(f"<red>{e}</red>") toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=False ) sys.exit(1) if not results["success"]: cli_message("Validation failed!") toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=True ) sys.exit(1) else: cli_message("Validation succeeded!") toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=True ) sys.exit(0) except Exception as e: toolkit.send_usage_message( data_context=context, event="cli.validation_operator.run", success=False ) raise e
def _suite_edit( suite, datasource, directory, jupyter, batch_kwargs, usage_event, suppress_usage_message=False, ): # suppress_usage_message flag is for the situation where _suite_edit is called by _suite_new(). # when called by _suite_new(), the flag will be set to False, otherwise it will default to True batch_kwargs_json = batch_kwargs batch_kwargs = None context = toolkit.load_data_context_with_error_handling(directory) try: suite = toolkit.load_expectation_suite(context, suite, usage_event) 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 ) ) if not suppress_usage_message: send_usage_message( data_context=context, event=usage_event, api_version="v2", success=True, ) sys.exit(1) except ge_exceptions.DataContextError: cli_message( "<red>Please check that your batch_kwargs are able to load a batch.</red>" ) if not suppress_usage_message: send_usage_message( data_context=context, event=usage_event, api_version="v2", 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 ) ) if not suppress_usage_message: send_usage_message( data_context=context, event=usage_event, api_version="v2", 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 = toolkit.select_datasource( context, datasource_name=datasource ) except ValueError as ve: cli_message(f"<red>{ve}</red>") send_usage_message( data_context=context, event=usage_event, api_version="v2", success=False, ) sys.exit(1) if not data_source: cli_message("<red>No datasources found in the context.</red>") if not suppress_usage_message: send_usage_message( data_context=context, event=usage_event, api_version="v2", 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, data_asset_name=None, additional_batch_kwargs=additional_batch_kwargs, ) notebook_name = f"edit_{suite.expectation_suite_name}.ipynb" notebook_path = _get_notebook_path(context, notebook_name) SuiteEditNotebookRenderer.from_data_context(context).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 ) if not suppress_usage_message: send_usage_message( data_context=context, event=usage_event, event_payload=payload, api_version="v2", success=True, ) if jupyter: toolkit.launch_jupyter_notebook(notebook_path) except Exception as e: send_usage_message( data_context=context, event=usage_event, api_version="v2", success=False, ) raise e