def docs_list(directory) -> None:
"""List known Data Docs Sites."""
context = toolkit.load_data_context_with_error_handling(directory)
docs_sites_url_dicts = context.get_docs_sites_urls()
docs_sites_strings = [
" - <cyan>{}</cyan>: {}".format(
docs_site_dict["site_name"],
docs_site_dict.get("site_url") or
f"site configured but does not exist. Run the following command to build site: great_expectations "
f'docs build --site-name {docs_site_dict["site_name"]}',
) for docs_site_dict in docs_sites_url_dicts
]
if len(docs_sites_strings) == 0:
cli_message("No Data Docs sites found")
else:
list_intro_string = _build_intro_string(docs_sites_strings)
cli_message_list(docs_sites_strings, list_intro_string)
send_usage_message(
data_context=context,
event="cli.docs.list",
api_version="v2",
success=True,
)
def clean_data_docs(directory, site_name=None, all=None) -> None:
"""Delete data docs"""
context = toolkit.load_data_context_with_error_handling(directory)
failed = True
if site_name is None and all is None:
cli_message("<red>{}</red>".format(
"Please specify --all to remove all sites or specify a specific site using "
"--site_name"))
sys.exit(1)
context.clean_data_docs(site_name=site_name)
failed = False
if not failed and context is not None:
send_usage_message(
data_context=context,
event="cli.docs.clean",
api_version="v2",
success=True,
)
cli_message("<green>Cleaned data docs</green>")
if failed and context is not None:
send_usage_message(
data_context=context,
event="cli.docs.clean",
api_version="v2",
success=False,
)
def checkpoint_run(checkpoint, directory):
"""Run a checkpoint. (Experimental)"""
usage_event = "cli.checkpoint.run"
context = toolkit.load_data_context_with_error_handling(
directory=directory, from_cli_upgrade_command=False
)
checkpoint: Checkpoint = toolkit.load_checkpoint(
context,
checkpoint,
usage_event,
)
try:
results = checkpoint.run()
except Exception as e:
toolkit.exit_with_failure_message_and_stats(
context, usage_event, f"<red>{e}</red>"
)
if not results["success"]:
cli_message("Validation failed!")
toolkit.send_usage_message(context, event=usage_event, success=True)
print_validation_operator_results_details(results)
sys.exit(1)
cli_message("Validation succeeded!")
toolkit.send_usage_message(context, event=usage_event, success=True)
print_validation_operator_results_details(results)
sys.exit(0)
def checkpoint_list(directory) -> None:
"""List configured checkpoints. (Experimental)"""
context = toolkit.load_data_context_with_error_handling(directory)
checkpoints = context.list_checkpoints()
if not checkpoints:
cli_message(
"No checkpoints found.\n"
" - Use the command `great_expectations checkpoint new` to create one."
)
send_usage_message(
data_context=context,
event="cli.checkpoint.list",
api_version="v2",
success=True,
)
sys.exit(0)
number_found = len(checkpoints)
plural = "s" if number_found > 1 else ""
message = f"Found {number_found} checkpoint{plural}."
pretty_list = [f" - <cyan>{cp}</cyan>" for cp in checkpoints]
cli_message_list(pretty_list, list_intro_string=message)
send_usage_message(
data_context=context,
event="cli.checkpoint.list",
api_version="v2",
success=True,
)
def confirm_proceed_or_exit(
confirm_prompt: str = "Would you like to proceed?",
continuation_message: str = "Ok, exiting now. You can always read more at https://docs.greatexpectations.io/ !",
exit_on_no: bool = True,
exit_code: int = 0,
) -> Optional[bool]:
"""
Every CLI command that starts a potentially lengthy (>1 sec) computation
or modifies some resources (e.g., edits the config file, adds objects
to the stores) must follow this pattern:
1. Explain which resources will be created/modified/deleted
2. Use this method to ask for user's confirmation
The goal of this standardization is for the users to expect consistency -
if you saw one command, you know what to expect from all others.
If the user does not confirm, the program should exit. The purpose of the exit_on_no parameter is to provide
the option to perform cleanup actions before exiting outside of the function.
"""
confirm_prompt_colorized = cli_colorize_string(confirm_prompt)
continuation_message_colorized = cli_colorize_string(continuation_message)
if not click.confirm(confirm_prompt_colorized, default=True):
if exit_on_no:
cli_message(continuation_message_colorized)
sys.exit(exit_code)
else:
return False
return True
def suite_delete(suite, directory):
"""
Delete an expectation suite from the expectation store.
"""
usage_event = "cli.suite.delete"
context = toolkit.load_data_context_with_error_handling(directory)
suite_names = context.list_expectation_suite_names()
if not suite_names:
toolkit.exit_with_failure_message_and_stats(
context,
usage_event,
"</red>No expectation suites found in the project.</red>",
)
if suite not in suite_names:
toolkit.exit_with_failure_message_and_stats(
context, usage_event, f"No expectation suite named {suite} found."
)
context.delete_expectation_suite(suite)
cli_message(f"Deleted the expectation suite named: {suite}")
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=True,
)
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_script(checkpoint, directory):
"""
Create a python script to run a checkpoint. (Experimental)
Checkpoints can be run directly without this script using the
`great_expectations checkpoint run` command.
This script is provided for those who wish to run checkpoints via python.
"""
context = toolkit.load_data_context_with_error_handling(directory)
usage_event = "cli.checkpoint.script"
# Attempt to load the checkpoint and deal with errors
_ = toolkit.load_checkpoint(context, checkpoint, usage_event)
script_name = f"run_{checkpoint}.py"
script_path = os.path.join(
context.root_directory, context.GE_UNCOMMITTED_DIR, script_name
)
if os.path.isfile(script_path):
toolkit.exit_with_failure_message_and_stats(
context,
usage_event,
f"""<red>Warning! A script named {script_name} already exists and this command will not overwrite it.</red>
- Existing file path: {script_path}""",
)
_write_checkpoint_script_to_disk(context.root_directory, checkpoint, script_path)
cli_message(
f"""<green>A python script was created that runs the checkpoint named: `{checkpoint}`</green>
- The script is located in `great_expectations/uncommitted/run_{checkpoint}.py`
- The script can be run with `python great_expectations/uncommitted/run_{checkpoint}.py`"""
)
toolkit.send_usage_message(context, event=usage_event, success=True)
def suite_list(directory):
"""Lists available Expectation Suites."""
context = toolkit.load_data_context_with_error_handling(directory)
try:
suite_names = [
f" - <cyan>{suite_name}</cyan>"
for suite_name in context.list_expectation_suite_names()
]
if len(suite_names) == 0:
cli_message("No Expectation Suites found")
toolkit.send_usage_message(data_context=context,
event="cli.suite.list",
success=True)
return
elif len(suite_names) == 1:
list_intro_string = "1 Expectation Suite found:"
else:
list_intro_string = f"{len(suite_names)} Expectation Suites found:"
cli_message_list(suite_names, list_intro_string)
toolkit.send_usage_message(data_context=context,
event="cli.suite.list",
success=True)
except Exception as e:
toolkit.send_usage_message(data_context=context,
event="cli.suite.list",
success=False)
raise e
def select_datasource(context: DataContext, datasource_name: str = None) -> Datasource:
"""Select a datasource interactively."""
# TODO consolidate all the myriad CLI tests into this
data_source = None
if datasource_name is None:
data_sources = sorted(context.list_datasources(), key=lambda x: x["name"])
if len(data_sources) == 0:
cli_message(
"<red>No datasources found in the context. To add a datasource, run `great_expectations datasource new`</red>"
)
elif len(data_sources) == 1:
datasource_name = data_sources[0]["name"]
else:
choices = "\n".join(
[
" {}. {}".format(i, data_source["name"])
for i, data_source in enumerate(data_sources, 1)
]
)
option_selection = click.prompt(
"Select a datasource" + "\n" + choices + "\n",
type=click.Choice(
[str(i) for i, data_source in enumerate(data_sources, 1)]
),
show_choices=False,
)
datasource_name = data_sources[int(option_selection) - 1]["name"]
if datasource_name is not None:
data_source = context.get_datasource(datasource_name)
return data_source
def load_data_context_with_error_handling(
directory: str, from_cli_upgrade_command: bool = False
) -> DataContext:
"""Return a DataContext with good error handling and exit codes."""
try:
context: DataContext = DataContext(context_root_dir=directory)
ge_config_version: int = context.get_config().config_version
if (
from_cli_upgrade_command
and int(ge_config_version) < CURRENT_GE_CONFIG_VERSION
):
directory = directory or context.root_directory
(
increment_version,
exception_occurred,
) = upgrade_project_one_version_increment(
context_root_dir=directory,
ge_config_version=ge_config_version,
continuation_message=EXIT_UPGRADE_CONTINUATION_MESSAGE,
from_cli_upgrade_command=from_cli_upgrade_command,
)
if not exception_occurred and increment_version:
context = DataContext(context_root_dir=directory)
return context
except ge_exceptions.UnsupportedConfigVersionError as err:
directory = directory or DataContext.find_context_root_dir()
ge_config_version = DataContext.get_ge_config_version(
context_root_dir=directory
)
upgrade_helper_class = (
GE_UPGRADE_HELPER_VERSION_MAP.get(int(ge_config_version))
if ge_config_version
else None
)
if upgrade_helper_class and ge_config_version < CURRENT_GE_CONFIG_VERSION:
upgrade_project(
context_root_dir=directory,
ge_config_version=ge_config_version,
from_cli_upgrade_command=from_cli_upgrade_command,
)
else:
cli_message(f"<red>{err.message}</red>")
sys.exit(1)
except (
ge_exceptions.ConfigNotFoundError,
ge_exceptions.InvalidConfigError,
) as err:
cli_message(f"<red>{err.message}</red>")
sys.exit(1)
except ge_exceptions.PluginModuleNotFoundError as err:
cli_message(err.cli.v012_colored_message)
sys.exit(1)
except ge_exceptions.PluginClassNotFoundError as err:
cli_message(err.cli.v012_colored_message)
sys.exit(1)
except ge_exceptions.InvalidConfigurationYamlError as err:
cli_message(f"<red>{str(err)}</red>")
sys.exit(1)
def upgrade_project(context_root_dir,
ge_config_version,
from_cli_upgrade_command=False) -> None:
if from_cli_upgrade_command:
message = (
f"<red>\nYour project appears to have an out-of-date config version ({ge_config_version}) - "
f"the version "
f"number must be at least {CURRENT_GE_CONFIG_VERSION}.</red>")
else:
message = (
f"<red>\nYour project appears to have an out-of-date config version ({ge_config_version}) - "
f"the version "
f"number must be at least {CURRENT_GE_CONFIG_VERSION}.\nIn order to proceed, "
f"your project must be upgraded.</red>")
cli_message(message)
upgrade_prompt = (
"\nWould you like to run the Upgrade Helper to bring your project up-to-date?"
)
confirm_proceed_or_exit(
confirm_prompt=upgrade_prompt,
continuation_message=EXIT_UPGRADE_CONTINUATION_MESSAGE,
)
cli_message(SECTION_SEPARATOR)
# use loop in case multiple upgrades need to take place
while ge_config_version < CURRENT_GE_CONFIG_VERSION:
(
increment_version,
exception_occurred,
) = upgrade_project_up_to_one_version_increment(
context_root_dir=context_root_dir,
ge_config_version=ge_config_version,
continuation_message=EXIT_UPGRADE_CONTINUATION_MESSAGE,
from_cli_upgrade_command=from_cli_upgrade_command,
)
if exception_occurred or not increment_version:
break
ge_config_version += 1
cli_message(SECTION_SEPARATOR)
upgrade_success_message = "<green>Upgrade complete. Exiting...</green>\n"
upgrade_incomplete_message = f"""\
<red>The Upgrade Helper was unable to perform a complete project upgrade. Next steps:</red>
- Please perform any manual steps outlined in the Upgrade Overview and/or Upgrade Report above
- When complete, increment the config_version key in your <cyan>great_expectations.yml</cyan> to <cyan>{
ge_config_version + 1}</cyan>\n
To learn more about the upgrade process, visit \
<cyan>https://docs.greatexpectations.io/en/latest/how_to_guides/migrating_versions.html</cyan>
"""
if ge_config_version < CURRENT_GE_CONFIG_VERSION:
cli_message(upgrade_incomplete_message)
else:
cli_message(upgrade_success_message)
sys.exit(0)
def exit_with_failure_message_and_stats(context: DataContext, usage_event: str,
message: str) -> None:
cli_message(message)
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=False,
)
sys.exit(1)
def validation_operator_list(directory):
"""List known Validation Operators."""
try:
context = DataContext(directory)
except ge_exceptions.ConfigNotFoundError as err:
cli_message(f"<red>{err.message}</red>")
return
try:
validation_operators = context.list_validation_operators()
if len(validation_operators) == 0:
cli_message("No Validation Operators found")
return
elif len(validation_operators) == 1:
list_intro_string = "1 Validation Operator found:"
else:
list_intro_string = "{} Validation Operators found:".format(
len(validation_operators)
)
cli_message(list_intro_string)
for validation_operator in validation_operators:
cli_message("")
cli_message_dict(validation_operator)
toolkit.send_usage_message(
data_context=context, event="cli.validation_operator.list", success=True
)
except Exception as e:
toolkit.send_usage_message(
data_context=context, event="cli.validation_operator.list", success=False
)
raise e
def _suite_scaffold(suite: str, directory: str, jupyter: bool) -> None:
usage_event = "cli.suite.scaffold"
suite_name = suite
context = toolkit.load_data_context_with_error_handling(directory)
notebook_filename = f"scaffold_{suite_name}.ipynb"
notebook_path = _get_notebook_path(context, notebook_filename)
if suite_name in context.list_expectation_suite_names():
toolkit.tell_user_suite_exists(suite_name)
if os.path.isfile(notebook_path):
cli_message(
f" - If you wish to adjust your scaffolding, you can open this notebook with jupyter: `{notebook_path}` <red>(Please note that if you run that notebook, you will overwrite your existing suite.)</red>"
)
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=False,
)
sys.exit(1)
datasource = toolkit.select_datasource(context)
if datasource is None:
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=False,
)
sys.exit(1)
_suite = context.create_expectation_suite(suite_name)
_, _, _, batch_kwargs = get_batch_kwargs(context,
datasource_name=datasource.name)
renderer = SuiteScaffoldNotebookRenderer(context, _suite, batch_kwargs)
renderer.render_to_disk(notebook_path)
send_usage_message(
data_context=context,
event=usage_event,
api_version="v2",
success=True,
)
if jupyter:
toolkit.launch_jupyter_notebook(notebook_path)
else:
cli_message(
f"To continue scaffolding this suite, run `jupyter notebook {notebook_path}`"
)
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 create_empty_suite(context: DataContext, expectation_suite_name: str,
batch_kwargs) -> None:
cli_message("""
Great Expectations will create a new Expectation Suite '{:s}' and store it here:
{:s}
""".format(
expectation_suite_name,
context.stores[
context.expectations_store_name].store_backend.get_url_for_key(
ExpectationSuiteIdentifier(
expectation_suite_name=expectation_suite_name).to_tuple()),
))
suite = context.create_expectation_suite(expectation_suite_name)
suite.add_citation(comment="New suite added via CLI",
batch_kwargs=batch_kwargs)
context.save_expectation_suite(suite, expectation_suite_name)
def _slack_setup(context):
webhook_url = None
cli_message(SLACK_SETUP_INTRO)
if not click.confirm(SLACK_SETUP_PROMPT, default=True):
cli_message(SLACK_LATER)
return context
else:
webhook_url = click.prompt(SLACK_WEBHOOK_PROMPT, default="")
while not is_sane_slack_webhook(webhook_url):
cli_message("That URL was not valid.\n")
if not click.confirm(SLACK_SETUP_PROMPT, default=True):
cli_message(SLACK_LATER)
return context
webhook_url = click.prompt(SLACK_WEBHOOK_PROMPT, default="")
context.save_config_variable("validation_notification_slack_webhook", webhook_url)
cli_message(SLACK_SETUP_COMPLETE)
return context
def project_check_config(directory):
"""Check a config for validity and help with migrations."""
cli_message("Checking your config files for validity...\n")
is_config_ok, error_message, context = do_config_check(directory)
if context:
toolkit.send_usage_message(data_context=context,
event="cli.project.check_config",
success=True)
if not is_config_ok:
cli_message("Unfortunately, your config appears to be invalid:\n")
cli_message(f"<red>{error_message}</red>")
sys.exit(1)
cli_message("<green>Your config file appears valid!</green>")
def store_list(directory):
"""List known Stores."""
context = toolkit.load_data_context_with_error_handling(directory)
try:
stores = context.list_stores()
if len(stores) == 0:
cli_message("No Stores found")
toolkit.send_usage_message(data_context=context,
event="cli.store.list",
success=True)
return
elif len(stores) == 1:
list_intro_string = "1 Store found:"
else:
list_intro_string = "{} Stores found:".format(len(stores))
cli_message(list_intro_string)
for store in stores:
cli_message("")
cli_message_dict(store)
toolkit.send_usage_message(data_context=context,
event="cli.store.list",
success=True)
except Exception as e:
toolkit.send_usage_message(data_context=context,
event="cli.store.list",
success=False)
raise e
def build_docs(context, site_name=None, view=True, assume_yes=False) -> None:
"""Build documentation in a context"""
logger.debug("Starting cli.datasource.build_docs")
if site_name is not None:
site_names = [site_name]
else:
site_names = None
index_page_locator_infos = context.build_data_docs(site_names=site_names,
dry_run=True)
msg = "\nThe following Data Docs sites will be built:\n\n"
for site_name, index_page_locator_info in index_page_locator_infos.items():
msg += f" - <cyan>{site_name}:</cyan> "
msg += f"{index_page_locator_info}\n"
cli_message(msg)
if not assume_yes:
toolkit.confirm_proceed_or_exit()
cli_message("\nBuilding Data Docs...\n")
context.build_data_docs(site_names=site_names)
cli_message("Done building Data Docs")
if view:
context.open_data_docs(site_name=site_name, only_if_exists=True)
def project_upgrade(directory):
"""Upgrade a project after installing the next Great Expectations major version."""
cli_message("\nChecking project...")
cli_message(SECTION_SEPARATOR)
if load_data_context_with_error_handling(directory=directory,
from_cli_upgrade_command=True):
up_to_date_message = (
"Your project is up-to-date - no further upgrade is necessary.\n")
cli_message(f"<green>{up_to_date_message}</green>")
sys.exit(0)
def _profile_to_create_a_suite(
additional_batch_kwargs,
batch_kwargs,
batch_kwargs_generator_name,
context,
datasource_name,
expectation_suite_name,
data_asset_name,
profiler_configuration,
):
cli_message(
"""
Great Expectations will choose a couple of columns and generate expectations about them
to demonstrate some examples of assertions you can make about your data.
Great Expectations will store these expectations in a new Expectation Suite '{:s}' here:
{:s}
""".format(
expectation_suite_name,
context.stores[
context.expectations_store_name
].store_backend.get_url_for_key(
ExpectationSuiteIdentifier(
expectation_suite_name=expectation_suite_name
).to_tuple()
),
)
)
confirm_proceed_or_exit()
# TODO this may not apply
cli_message("\nGenerating example Expectation Suite...")
run_id = datetime.datetime.now(datetime.timezone.utc).strftime("%Y%m%dT%H%M%S.%fZ")
profiling_results = context.profile_data_asset(
datasource_name,
batch_kwargs_generator_name=batch_kwargs_generator_name,
data_asset_name=data_asset_name,
batch_kwargs=batch_kwargs,
profiler=BasicSuiteBuilderProfiler,
profiler_configuration=profiler_configuration,
expectation_suite_name=expectation_suite_name,
run_id=run_id,
additional_batch_kwargs=additional_batch_kwargs,
)
if not profiling_results["success"]:
_raise_profiling_errors(profiling_results)
cli_message("\nDone generating example Expectation Suite")
return profiling_results
def checkpoint_run(checkpoint, directory):
"""Run a checkpoint. (Experimental)"""
usage_event = "cli.checkpoint.run"
context = toolkit.load_data_context_with_error_handling(
directory=directory, from_cli_upgrade_command=False)
ge_config_version = context.get_config().config_version
if ge_config_version >= 3:
cli_message(
f"""<red>The `checkpoint run` 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)
checkpoint: Checkpoint = toolkit.load_checkpoint(
context,
checkpoint,
usage_event,
)
try:
results = checkpoint.run()
except Exception as e:
toolkit.exit_with_failure_message_and_stats(context, usage_event,
f"<red>{e}</red>")
if not results["success"]:
cli_message("Validation failed!")
toolkit.send_usage_message(context, event=usage_event, success=True)
print_validation_operator_results_details(results)
sys.exit(1)
cli_message("Validation succeeded!")
toolkit.send_usage_message(context, event=usage_event, success=True)
print_validation_operator_results_details(results)
sys.exit(0)
def create_expectation_suite(
context,
datasource_name=None,
batch_kwargs_generator_name=None,
generator_asset=None,
batch_kwargs=None,
expectation_suite_name=None,
additional_batch_kwargs=None,
empty_suite=False,
show_intro_message=False,
flag_build_docs=True,
open_docs=False,
profiler_configuration="demo",
data_asset_name=None,
):
"""
Create a new expectation suite.
WARNING: the flow and name of this method and its interaction with _profile_to_create_a_suite
require a serious revisiting.
:return: a tuple: (success, suite name, profiling_results)
"""
if generator_asset:
warnings.warn(
"The 'generator_asset' argument will be deprecated and renamed to 'data_asset_name'. "
"Please update code accordingly.",
DeprecationWarning,
)
data_asset_name = generator_asset
if show_intro_message and not empty_suite:
cli_message(
"\n<cyan>========== Create sample Expectations ==========</cyan>\n\n"
)
data_source = select_datasource(context, datasource_name=datasource_name)
if data_source is None:
# select_datasource takes care of displaying an error message, so all is left here is to exit.
sys.exit(1)
datasource_name = data_source.name
if expectation_suite_name in context.list_expectation_suite_names():
tell_user_suite_exists(expectation_suite_name)
sys.exit(1)
if (
batch_kwargs_generator_name is None
or data_asset_name is None
or batch_kwargs is None
):
(
datasource_name,
batch_kwargs_generator_name,
data_asset_name,
batch_kwargs,
) = get_batch_kwargs(
context,
datasource_name=datasource_name,
batch_kwargs_generator_name=batch_kwargs_generator_name,
data_asset_name=data_asset_name,
additional_batch_kwargs=additional_batch_kwargs,
)
# In this case, we have "consumed" the additional_batch_kwargs
additional_batch_kwargs = {}
if expectation_suite_name is None:
default_expectation_suite_name = _get_default_expectation_suite_name(
batch_kwargs, data_asset_name
)
while True:
expectation_suite_name = click.prompt(
"\nName the new Expectation Suite",
default=default_expectation_suite_name,
)
if expectation_suite_name in context.list_expectation_suite_names():
tell_user_suite_exists(expectation_suite_name)
else:
break
if empty_suite:
create_empty_suite(context, expectation_suite_name, batch_kwargs)
return True, expectation_suite_name, None
profiling_results = _profile_to_create_a_suite(
additional_batch_kwargs,
batch_kwargs,
batch_kwargs_generator_name,
context,
datasource_name,
expectation_suite_name,
data_asset_name,
profiler_configuration,
)
if flag_build_docs:
build_docs(context, view=False)
if open_docs:
attempt_to_open_validation_results_in_data_docs(context, profiling_results)
return True, expectation_suite_name, profiling_results
def upgrade_project_one_version_increment(
context_root_dir: str,
ge_config_version: float,
continuation_message: str,
from_cli_upgrade_command: bool = False,
) -> [bool, bool]: # Returns increment_version, exception_occurred
upgrade_helper_class = GE_UPGRADE_HELPER_VERSION_MAP.get(int(ge_config_version))
if not upgrade_helper_class:
return False, False
target_ge_config_version = int(ge_config_version) + 1
# set version temporarily to CURRENT_GE_CONFIG_VERSION to get functional DataContext
DataContext.set_ge_config_version(
config_version=CURRENT_GE_CONFIG_VERSION,
context_root_dir=context_root_dir,
)
upgrade_helper = upgrade_helper_class(context_root_dir=context_root_dir)
upgrade_overview, confirmation_required = upgrade_helper.get_upgrade_overview()
if confirmation_required or from_cli_upgrade_command:
upgrade_confirmed = confirm_proceed_or_exit(
confirm_prompt=upgrade_overview,
continuation_message=continuation_message,
exit_on_no=False,
)
else:
upgrade_confirmed = True
if upgrade_confirmed:
cli_message("\nUpgrading project...")
cli_message(SECTION_SEPARATOR)
# run upgrade and get report of what was done, if version number should be incremented
(
upgrade_report,
increment_version,
exception_occurred,
) = upgrade_helper.upgrade_project()
# display report to user
cli_message(upgrade_report)
if exception_occurred:
# restore version number to current number
DataContext.set_ge_config_version(
ge_config_version, context_root_dir, validate_config_version=False
)
# display report to user
return False, True
# set config version to target version
if increment_version:
DataContext.set_ge_config_version(
target_ge_config_version,
context_root_dir,
validate_config_version=False,
)
return True, False
# restore version number to current number
DataContext.set_ge_config_version(
ge_config_version, context_root_dir, validate_config_version=False
)
return False, False
# restore version number to current number
DataContext.set_ge_config_version(
ge_config_version, context_root_dir, validate_config_version=False
)
cli_message(continuation_message)
sys.exit(0)
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
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 exit_with_failure_message_and_stats(
context: DataContext, usage_event: str, message: str
) -> None:
cli_message(message)
send_usage_message(context, event=usage_event, success=False)
sys.exit(1)
def tell_user_suite_exists(suite_name: str) -> None:
cli_message(
f"""<red>An expectation suite named `{suite_name}` already exists.</red>
- If you intend to edit the suite please use `great_expectations suite edit {suite_name}`."""
)
