コード例 #1
0
def validation_operator_list(directory):
    """Lists the names of the validation operators configured in the project."""
    try:
        context = DataContext(directory)
    except ge_exceptions.ConfigNotFoundError as err:
        cli_message("<red>{}</red>".format(err.message))
        return

    suite_names = context.list_validation_operator_names()
    if len(suite_names) == 0:
        cli_message("No validation operators are configured in the project")
        return

    if len(suite_names) == 1:
        cli_message("1 validation operator found:")

    if len(suite_names) > 1:
        cli_message("{} validation operators found:".format(len(suite_names)))

    for name in suite_names:
        cli_message("\t{}".format(name))
コード例 #2
0
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("Failed to process <red>{}</red>".format(err.message))
        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>"
                )
                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))
                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.
""")
                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.
""")
                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.
""")
                    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("<red>{}</red>".format(ve))
                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>")
                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("<red>{}</red>".format(e))
            send_usage_message(data_context=context,
                               event="cli.validation_operator.run",
                               success=False)
            sys.exit(1)

        if not results["success"]:
            cli_message("Validation failed!")
            send_usage_message(data_context=context,
                               event="cli.validation_operator.run",
                               success=True)
            sys.exit(1)
        else:
            cli_message("Validation succeeded!")
            send_usage_message(data_context=context,
                               event="cli.validation_operator.run",
                               success=True)
            sys.exit(0)
    except Exception as e:
        send_usage_message(data_context=context,
                           event="cli.validation_operator.run",
                           success=False)
        raise e