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 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_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 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 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 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 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 docs_build(directory, site_name, view=True, assume_yes=False): """Build Data Docs for a project.""" context = toolkit.load_data_context_with_error_handling(directory) build_docs(context, site_name=site_name, view=view, assume_yes=assume_yes) toolkit.send_usage_message(data_context=context, event="cli.docs.build", 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 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 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 _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 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 _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 _suite_new( suite: str, directory: str, empty: bool, jupyter: bool, view: bool, batch_kwargs, usage_event: str, ) -> None: # TODO break this up into demo and new context = toolkit.load_data_context_with_error_handling(directory) datasource_name = None generator_name = None data_asset_name = None try: if batch_kwargs is not None: batch_kwargs = json.loads(batch_kwargs) success, suite_name, profiling_results = toolkit.create_expectation_suite( context, datasource_name=datasource_name, batch_kwargs_generator_name=generator_name, data_asset_name=data_asset_name, batch_kwargs=batch_kwargs, expectation_suite_name=suite, additional_batch_kwargs={"limit": 1000}, empty_suite=empty, show_intro_message=False, open_docs=view, ) if success: if empty: if jupyter: cli_message( """<green>Because you requested an empty suite, we'll open a notebook for you now to edit it! If you wish to avoid this you can add the `--no-jupyter` flag.</green>\n\n""" ) send_usage_message( data_context=context, event=usage_event, api_version="v2", success=True, ) _suite_edit( suite_name, datasource_name, directory, jupyter=jupyter, batch_kwargs=batch_kwargs, usage_event="cli.suite.edit", # or else we will be sending `cli.suite.new` which is incorrect suppress_usage_message=True, # dont want actually send usage_message since the function call is not the result of actual usage ) else: send_usage_message( data_context=context, event=usage_event, api_version="v2", success=False, ) except ( ge_exceptions.DataContextError, ge_exceptions.ProfilerError, OSError, SQLAlchemyError, ) as e: cli_message(f"<red>{e}</red>") send_usage_message( data_context=context, event=usage_event, api_version="v2", success=False, ) sys.exit(1) except Exception as e: send_usage_message( data_context=context, event=usage_event, api_version="v2", success=False, ) raise e