def test_cli_datasorce_new(caplog, empty_data_context, filesystem_csv_2):
project_root_dir = empty_data_context.root_directory
context = DataContext(project_root_dir)
assert context.list_datasources() == []
runner = CliRunner(mix_stderr=False)
result = runner.invoke(
cli,
["datasource", "new", "-d", project_root_dir],
input="1\n1\n%s\nmynewsource\n" % str(filesystem_csv_2),
catch_exceptions=False,
)
stdout = result.stdout
assert "What data would you like Great Expectations to connect to?" in stdout
assert "What are you processing your files with?" in stdout
assert "Give your new Datasource a short name." in stdout
assert "A new datasource 'mynewsource' was added to your project." in stdout
assert result.exit_code == 0
config_path = os.path.join(project_root_dir, DataContext.GE_YML)
config = yaml.load(open(config_path))
datasources = config["datasources"]
assert "mynewsource" in datasources.keys()
data_source_class = datasources["mynewsource"]["data_asset_type"][
"class_name"]
assert data_source_class == "PandasDataset"
assert_no_logging_messages_or_tracebacks(caplog, result)
def _load_config_file(config_path):
assert os.path.isfile(config_path), "Config file is missing. Check path"
with open(config_path) as f:
read = f.read()
config = yaml.load(read)
assert isinstance(config, dict)
return config
def test_cli_init_on_new_project_with_broken_excel_file_without_trying_again(
caplog, tmp_path_factory
):
project_dir = str(tmp_path_factory.mktemp("test_cli_init_diff"))
os.makedirs(os.path.join(project_dir, "data"))
data_folder_path = os.path.join(project_dir, "data")
data_path = os.path.join(project_dir, "data", "broken_excel_file.xls")
fixture_path = file_relative_path(__file__, "../../test_sets/broken_excel_file.xls")
shutil.copy(fixture_path, data_path)
runner = CliRunner(mix_stderr=False)
result = runner.invoke(
cli,
["init", "-d", project_dir],
input=f"\n\n1\n1\n{data_folder_path}\n\n\n\n2\n{data_path}\nn\n",
catch_exceptions=False,
)
stdout = result.output
assert len(stdout) < 6000, "CLI output is unreasonably long."
assert "Always know what to expect from your data" in stdout
assert "What data would you like Great Expectations to connect to" in stdout
assert "What are you processing your files with" in stdout
assert (
"Enter the path of a data file (relative or absolute, s3a:// and gs:// paths are ok too)"
in stdout
)
assert "Cannot load file." in stdout
assert (
"- Please check the file and try again or select a different data file."
in stdout
)
assert (
"- Error: Excel file format cannot be determined, you must specify an engine manually."
in stdout
) or (
"Error: Unsupported format, or corrupt file: Expected BOF record; found b'PRODUCTI'"
in stdout
)
assert "Try again? [Y/n]:" in stdout
assert (
"We have saved your setup progress. When you are ready, run great_expectations init to continue."
in stdout
)
assert os.path.isdir(os.path.join(project_dir, "great_expectations"))
config_path = os.path.join(project_dir, "great_expectations/great_expectations.yml")
assert os.path.isfile(config_path)
config = yaml.load(open(config_path))
data_source_class = config["datasources"]["data__dir"]["data_asset_type"][
"class_name"
]
assert data_source_class == "PandasDataset"
assert_no_logging_messages_or_tracebacks(caplog, result)
def test_cli_datasource_new_connection_string(
empty_data_context, empty_sqlite_db, caplog
):
project_root_dir = empty_data_context.root_directory
context = DataContext(project_root_dir)
assert context.list_datasources() == []
runner = CliRunner(mix_stderr=False)
result = runner.invoke(
cli,
["datasource", "new", "-d", project_root_dir],
input="2\n6\nmynewsource\n{}\n\n".format(str(empty_sqlite_db.url)),
catch_exceptions=False,
)
stdout = result.stdout
assert "What data would you like Great Expectations to connect to?" in stdout
assert "Give your new Datasource a short name." in stdout
assert (
"Next, we will configure database credentials and store them in the `mynewsource` section"
in stdout
)
assert "What is the url/connection string for the sqlalchemy connection?" in stdout
assert "Attempting to connect to your database. This may take a moment" in stdout
assert "Great Expectations connected to your database" in stdout
assert "A new datasource 'mynewsource' was added to your project." in stdout
assert result.exit_code == 0
config_path = os.path.join(project_root_dir, DataContext.GE_YML)
config = yaml.load(open(config_path))
datasources = config["datasources"]
assert "mynewsource" in datasources.keys()
data_source_class = datasources["mynewsource"]["data_asset_type"]["class_name"]
assert data_source_class == "SqlAlchemyDataset"
assert_no_logging_messages_or_tracebacks(caplog, result)
def test_cli_init_on_new_project(mock_webbrowser, caplog, tmp_path_factory,
titanic_sqlite_db_file, sa):
project_dir = str(tmp_path_factory.mktemp("test_cli_init_diff"))
ge_dir = os.path.join(project_dir, "great_expectations")
database_path = os.path.join(project_dir, "titanic.db")
shutil.copy(titanic_sqlite_db_file, database_path)
engine = sa.create_engine(f"sqlite:///{database_path}", pool_recycle=3600)
inspector = sa.inspect(engine)
# get the default schema and table for testing
schemas = inspector.get_schema_names()
default_schema = schemas[0]
tables = [
table_name
for table_name in inspector.get_table_names(schema=default_schema)
]
default_table = tables[0]
runner = CliRunner(mix_stderr=False)
result = runner.invoke(
cli,
["init", "-d", project_dir],
input=
"\n\n2\n6\ntitanic\n{url}\n\n\n1\n{schema}\n{table}\nwarning\n\n\n\n".
format(url=engine.url, schema=default_schema, table=default_table),
catch_exceptions=False,
)
stdout = result.output
assert len(stdout) < 6000, "CLI output is unreasonably long."
assert "Always know what to expect from your data" in stdout
assert "What data would you like Great Expectations to connect to" in stdout
assert "Which database backend are you using" in stdout
assert "Give your new Datasource a short name" in stdout
assert "What is the url/connection string for the sqlalchemy connection" in stdout
assert "Attempting to connect to your database." in stdout
assert "Great Expectations connected to your database" in stdout
assert (
"You have selected a datasource that is a SQL database. How would you like to specify the data?"
in stdout)
assert "Name the new Expectation Suite [main.titanic.warning]" in stdout
assert (
"Great Expectations will choose a couple of columns and generate expectations about them"
in stdout)
assert "Generating example Expectation Suite..." in stdout
assert "Building" in stdout
assert "Data Docs" in stdout
assert "Great Expectations is now set up" in stdout
context = DataContext(ge_dir)
assert len(context.list_datasources()) == 1
assert context.list_datasources(
)[0]["class_name"] == "SqlAlchemyDatasource"
assert context.list_datasources()[0]["name"] == "titanic"
first_suite = context.list_expectation_suites()[0]
suite = context.get_expectation_suite(first_suite.expectation_suite_name)
assert len(suite.expectations) == 14
assert os.path.isdir(ge_dir)
config_path = os.path.join(project_dir,
"great_expectations/great_expectations.yml")
assert os.path.isfile(config_path)
config = yaml.load(open(config_path))
data_source_class = config["datasources"]["titanic"]["data_asset_type"][
"class_name"]
assert data_source_class == "SqlAlchemyDataset"
# Profilers are v014+ specific
os.rmdir(os.path.join(ge_dir, "profilers"))
obs_tree = gen_directory_tree_str(ge_dir)
# Instead of monkey patching guids, just regex out the guids
guid_safe_obs_tree = re.sub(r"[a-z0-9]{32}(?=\.(json|html))",
"foobarbazguid", obs_tree)
# print(guid_safe_obs_tree)
assert (guid_safe_obs_tree == """\
great_expectations/
.gitignore
great_expectations.yml
checkpoints/
expectations/
.ge_store_backend_id
warning.json
plugins/
custom_data_docs/
renderers/
styles/
data_docs_custom_styles.css
views/
uncommitted/
config_variables.yml
data_docs/
local_site/
index.html
expectations/
warning.html
static/
fonts/
HKGrotesk/
HKGrotesk-Bold.otf
HKGrotesk-BoldItalic.otf
HKGrotesk-Italic.otf
HKGrotesk-Light.otf
HKGrotesk-LightItalic.otf
HKGrotesk-Medium.otf
HKGrotesk-MediumItalic.otf
HKGrotesk-Regular.otf
HKGrotesk-SemiBold.otf
HKGrotesk-SemiBoldItalic.otf
images/
favicon.ico
glossary_scroller.gif
iterative-dev-loop.png
logo-long-vector.svg
logo-long.png
short-logo-vector.svg
short-logo.png
validation_failed_unexpected_values.gif
styles/
data_docs_custom_styles_template.css
data_docs_default_styles.css
validations/
warning/
20190926T134241.000000Z/
20190926T134241.000000Z/
foobarbazguid.html
validations/
.ge_store_backend_id
warning/
20190926T134241.000000Z/
20190926T134241.000000Z/
foobarbazguid.json
""")
assert_no_logging_messages_or_tracebacks(caplog, result)
assert result.exit_code == 0
assert mock_webbrowser.call_count == 1
assert (
"{}/great_expectations/uncommitted/data_docs/local_site/validations/warning/"
.format(project_dir) in mock_webbrowser.call_args[0][0])
def test_cli_init_on_new_project_extra_whitespace_in_url(
mock_webbrowser, caplog, tmp_path_factory, titanic_sqlite_db_file, sa):
project_dir = str(tmp_path_factory.mktemp("test_cli_init_diff"))
ge_dir = os.path.join(project_dir, "great_expectations")
database_path = os.path.join(project_dir, "titanic.db")
shutil.copy(titanic_sqlite_db_file, database_path)
engine = sa.create_engine(f"sqlite:///{database_path}", pool_recycle=3600)
engine_url_with_added_whitespace = " " + str(engine.url) + " "
inspector = sa.inspect(engine)
# get the default schema and table for testing
schemas = inspector.get_schema_names()
default_schema = schemas[0]
tables = [
table_name
for table_name in inspector.get_table_names(schema=default_schema)
]
default_table = tables[0]
runner = CliRunner(mix_stderr=False)
result = runner.invoke(
cli,
["init", "-d", project_dir],
input=
"\n\n2\n6\ntitanic\n{url}\n\n\n1\n{schema}\n{table}\nwarning\n\n\n\n".
format(
url=engine_url_with_added_whitespace,
schema=default_schema,
table=default_table,
),
catch_exceptions=False,
)
stdout = result.output
assert len(stdout) < 6000, "CLI output is unreasonably long."
assert "Always know what to expect from your data" in stdout
assert "What data would you like Great Expectations to connect to" in stdout
assert "Which database backend are you using" in stdout
assert "Give your new Datasource a short name" in stdout
assert "What is the url/connection string for the sqlalchemy connection" in stdout
assert "Attempting to connect to your database." in stdout
assert "Great Expectations connected to your database" in stdout
assert (
"You have selected a datasource that is a SQL database. How would you like to specify the data?"
in stdout)
assert "Name the new Expectation Suite [main.titanic.warning]" in stdout
assert (
"Great Expectations will choose a couple of columns and generate expectations about them"
in stdout)
assert "Generating example Expectation Suite..." in stdout
assert "Building" in stdout
assert "Data Docs" in stdout
assert "Great Expectations is now set up" in stdout
context = DataContext(ge_dir)
assert len(context.list_datasources()) == 1
assert context.list_datasources() == [{
"class_name": "SqlAlchemyDatasource",
"name": "titanic",
"module_name": "great_expectations.datasource",
"credentials": {
"url": str(engine.url)
},
"data_asset_type": {
"class_name": "SqlAlchemyDataset",
"module_name": "great_expectations.dataset",
},
}]
first_suite = context.list_expectation_suites()[0]
suite = context.get_expectation_suite(first_suite.expectation_suite_name)
assert len(suite.expectations) == 14
assert os.path.isdir(ge_dir)
config_path = os.path.join(project_dir,
"great_expectations/great_expectations.yml")
assert os.path.isfile(config_path)
config = yaml.load(open(config_path))
data_source_class = config["datasources"]["titanic"]["data_asset_type"][
"class_name"]
assert data_source_class == "SqlAlchemyDataset"
assert_no_logging_messages_or_tracebacks(caplog, result)
assert result.exit_code == 0
assert mock_webbrowser.call_count == 1
assert (
"{}/great_expectations/uncommitted/data_docs/local_site/validations/warning/"
.format(project_dir) in mock_webbrowser.call_args[0][0])
def test_cli_init_spark_without_library_installed_instructs_user(
caplog, tmp_path_factory):
basedir = tmp_path_factory.mktemp("test_cli_init_diff")
basedir = str(basedir)
with set_directory(basedir):
runner = CliRunner(mix_stderr=False)
result = runner.invoke(cli, ["init", "--no-view"],
input="\n\n1\n2\nn\n",
catch_exceptions=False)
stdout = result.output
assert "Always know what to expect from your data" in stdout
assert "What data would you like Great Expectations to connect to" in stdout
assert "What are you processing your files with" in stdout
assert (
"Great Expectations relies on the library `pyspark` to connect to your data"
in stdout)
assert (
"but the package `pyspark` containing this library is not installed."
in stdout)
assert (
"Would you like Great Expectations to try to execute `pip install pyspark` for you?"
in stdout)
assert "Please execute `pip install pyspark` before trying again." in stdout
# assert "Great Expectations relies on the library `pyspark`" in stdout
# assert "Please `pip install pyspark` before trying again" in stdout
assert "Profiling" not in stdout
assert "Building" not in stdout
assert "Data Docs" not in stdout
assert "Great Expectations is now set up" not in stdout
assert result.exit_code == 1
assert os.path.isdir(os.path.join(basedir, "great_expectations"))
config_path = os.path.join(
basedir, "great_expectations/great_expectations.yml")
assert os.path.isfile(config_path)
config = yaml.load(open(config_path))
assert config["datasources"] == {}
obs_tree = gen_directory_tree_str(
os.path.join(basedir, "great_expectations"))
assert (obs_tree == """\
great_expectations/
.gitignore
great_expectations.yml
checkpoints/
expectations/
.ge_store_backend_id
plugins/
custom_data_docs/
renderers/
styles/
data_docs_custom_styles.css
views/
profilers/
uncommitted/
config_variables.yml
data_docs/
validations/
.ge_store_backend_id
""")
assert_no_logging_messages_or_tracebacks(caplog, result)
def _library_not_loaded_test(tmp_path_factory, cli_input, library_name,
library_import_name, my_caplog):
"""
This test requires that a library is NOT installed. It tests that:
- a helpful error message is returned to install the missing library
- the expected tree structure is in place
- the config yml contains an empty dict in its datasource entry
"""
basedir = tmp_path_factory.mktemp("test_cli_init_diff")
basedir = str(basedir)
with set_directory(basedir):
runner = CliRunner(mix_stderr=False)
result = runner.invoke(cli, ["init", "--no-view"],
input=cli_input,
catch_exceptions=False)
stdout = result.output
assert "Always know what to expect from your data" in stdout
assert "What data would you like Great Expectations to connect to" in stdout
assert "Which database backend are you using" in stdout
assert "Give your new Datasource a short name" in stdout
assert (
"Next, we will configure database credentials and store them in the `my_db` section"
in stdout)
assert (
f"Great Expectations relies on the library `{library_import_name}` to connect to your data"
in stdout)
assert (
f"but the package `{library_name}` containing this library is not installed"
in stdout)
assert (
f"Would you like Great Expectations to try to execute `pip install {library_name}` for you?"
in stdout)
assert (
f"Please execute `pip install {library_name}` before trying again."
in stdout)
assert "Profiling" not in stdout
assert "Building" not in stdout
assert "Data Docs" not in stdout
assert "Great Expectations is now set up" not in stdout
assert result.exit_code == 1
assert os.path.isdir(os.path.join(basedir, "great_expectations"))
config_path = os.path.join(
basedir, "great_expectations/great_expectations.yml")
assert os.path.isfile(config_path)
config = yaml.load(open(config_path))
assert config["datasources"] == {}
obs_tree = gen_directory_tree_str(
os.path.join(basedir, "great_expectations"))
assert (obs_tree == """\
great_expectations/
.gitignore
great_expectations.yml
checkpoints/
expectations/
.ge_store_backend_id
plugins/
custom_data_docs/
renderers/
styles/
data_docs_custom_styles.css
views/
profilers/
uncommitted/
config_variables.yml
data_docs/
validations/
.ge_store_backend_id
""")
assert_no_logging_messages_or_tracebacks(my_caplog, result)
def test_cli_init_on_new_project_with_broken_excel_file_try_again_with_different_file(
mock_webbrowser, caplog, tmp_path_factory
):
project_dir = str(tmp_path_factory.mktemp("test_cli_init_diff"))
os.makedirs(os.path.join(project_dir, "data"))
data_folder_path = os.path.join(project_dir, "data")
data_path = os.path.join(project_dir, "data", "broken_excel_file.xls")
fixture_path = file_relative_path(__file__, "../../test_sets/broken_excel_file.xls")
data_path_2 = os.path.join(project_dir, "data", "Titanic.csv")
fixture_path_2 = file_relative_path(__file__, "../../test_sets/Titanic.csv")
shutil.copy(fixture_path, data_path)
shutil.copy(fixture_path_2, data_path_2)
runner = CliRunner(mix_stderr=False)
result = runner.invoke(
cli,
["init", "-d", project_dir],
input="\n\n1\n1\n{}\n\n\n\n2\n{}\n\n{}\n\n\n\n".format(
data_folder_path, data_path, data_path_2
),
catch_exceptions=False,
)
stdout = result.output
assert mock_webbrowser.call_count == 1
assert (
"{}/great_expectations/uncommitted/data_docs/local_site/validations/Titanic/warning/".format(
project_dir
)
in mock_webbrowser.call_args[0][0]
)
assert len(stdout) < 6000, "CLI output is unreasonably long."
assert "Always know what to expect from your data" in stdout
assert "What data would you like Great Expectations to connect to" in stdout
assert "What are you processing your files with" in stdout
assert (
"Enter the path of a data file (relative or absolute, s3a:// and gs:// paths are ok too)"
in stdout
)
assert "Cannot load file." in stdout
assert (
"- Please check the file and try again or select a different data file."
in stdout
)
assert (
"- Error: Excel file format cannot be determined, you must specify an engine manually."
in stdout
) or (
"Error: Unsupported format, or corrupt file: Expected BOF record; found b'PRODUCTI'"
in stdout
)
assert "Try again? [Y/n]:" in stdout
assert f"[{data_path}]:" in stdout
assert "Name the new Expectation Suite [Titanic.warning]" in stdout
assert (
"Great Expectations will choose a couple of columns and generate expectations about them"
in stdout
)
assert "Generating example Expectation Suite..." in stdout
assert "Building" in stdout
assert "Data Docs" in stdout
assert "Great Expectations is now set up" in stdout
assert os.path.isdir(os.path.join(project_dir, "great_expectations"))
config_path = os.path.join(project_dir, "great_expectations/great_expectations.yml")
assert os.path.isfile(config_path)
config = yaml.load(open(config_path))
data_source_class = config["datasources"]["data__dir"]["data_asset_type"][
"class_name"
]
assert data_source_class == "PandasDataset"
obs_tree = gen_directory_tree_str(os.path.join(project_dir, "great_expectations"))
# Instead of monkey patching guids, just regex out the guids
guid_safe_obs_tree = re.sub(
r"[a-z0-9]{32}(?=\.(json|html))", "foobarbazguid", obs_tree
)
# print(guid_safe_obs_tree)
assert (
guid_safe_obs_tree
== """great_expectations/
.gitignore
great_expectations.yml
checkpoints/
expectations/
.ge_store_backend_id
Titanic/
warning.json
notebooks/
pandas/
validation_playground.ipynb
spark/
validation_playground.ipynb
sql/
validation_playground.ipynb
plugins/
custom_data_docs/
renderers/
styles/
data_docs_custom_styles.css
views/
uncommitted/
config_variables.yml
data_docs/
local_site/
index.html
expectations/
Titanic/
warning.html
static/
fonts/
HKGrotesk/
HKGrotesk-Bold.otf
HKGrotesk-BoldItalic.otf
HKGrotesk-Italic.otf
HKGrotesk-Light.otf
HKGrotesk-LightItalic.otf
HKGrotesk-Medium.otf
HKGrotesk-MediumItalic.otf
HKGrotesk-Regular.otf
HKGrotesk-SemiBold.otf
HKGrotesk-SemiBoldItalic.otf
images/
favicon.ico
glossary_scroller.gif
iterative-dev-loop.png
logo-long-vector.svg
logo-long.png
short-logo-vector.svg
short-logo.png
validation_failed_unexpected_values.gif
styles/
data_docs_custom_styles_template.css
data_docs_default_styles.css
validations/
Titanic/
warning/
20190926T134241.000000Z/
20190926T134241.000000Z/
foobarbazguid.html
validations/
.ge_store_backend_id
Titanic/
warning/
20190926T134241.000000Z/
20190926T134241.000000Z/
foobarbazguid.json
"""
)
assert_no_logging_messages_or_tracebacks(caplog, result)
def test_cli_init_on_new_project(
mock_emit, mock_webbrowser, caplog, tmp_path_factory, monkeypatch
):
monkeypatch.delenv(
"GE_USAGE_STATS", raising=False
) # Undo the project-wide test default
project_dir = str(tmp_path_factory.mktemp("test_cli_init_diff"))
os.makedirs(os.path.join(project_dir, "data"))
data_folder_path = os.path.join(project_dir, "data")
data_path = os.path.join(project_dir, "data", "Titanic.csv")
fixture_path = file_relative_path(__file__, "../../test_sets/Titanic.csv")
shutil.copy(fixture_path, data_path)
runner = CliRunner(mix_stderr=False)
result = runner.invoke(
cli,
["init", "-d", project_dir],
input=f"\n\n1\n1\n{data_folder_path}\n\n\n\n2\n{data_path}\n\n\n\n",
catch_exceptions=False,
)
stdout = result.output
assert mock_webbrowser.call_count == 1
assert (
"{}/great_expectations/uncommitted/data_docs/local_site/validations/Titanic/warning/".format(
project_dir
)
in mock_webbrowser.call_args[0][0]
)
assert len(stdout) < 6000, "CLI output is unreasonably long."
assert "Always know what to expect from your data" in stdout
assert "What data would you like Great Expectations to connect to" in stdout
assert "What are you processing your files with" in stdout
assert (
"Enter the path of a data file (relative or absolute, s3a:// and gs:// paths are ok too)"
in stdout
)
assert "Name the new Expectation Suite [Titanic.warning]" in stdout
assert (
"Great Expectations will choose a couple of columns and generate expectations about them"
in stdout
)
assert "Generating example Expectation Suite..." in stdout
assert "Building" in stdout
assert "Data Docs" in stdout
assert "Done generating example Expectation Suite" in stdout
assert "Great Expectations is now set up" in stdout
assert os.path.isdir(os.path.join(project_dir, "great_expectations"))
config_path = os.path.join(project_dir, "great_expectations/great_expectations.yml")
assert os.path.isfile(config_path)
config = yaml.load(open(config_path))
data_source_class = config["datasources"]["data__dir"]["data_asset_type"][
"class_name"
]
assert data_source_class == "PandasDataset"
obs_tree = gen_directory_tree_str(os.path.join(project_dir, "great_expectations"))
# Instead of monkey patching guids, just regex out the guids
guid_safe_obs_tree = re.sub(
r"[a-z0-9]{32}(?=\.(json|html))", "foobarbazguid", obs_tree
)
# print(guid_safe_obs_tree)
assert (
guid_safe_obs_tree
== """great_expectations/
.gitignore
great_expectations.yml
checkpoints/
expectations/
.ge_store_backend_id
Titanic/
warning.json
notebooks/
pandas/
validation_playground.ipynb
spark/
validation_playground.ipynb
sql/
validation_playground.ipynb
plugins/
custom_data_docs/
renderers/
styles/
data_docs_custom_styles.css
views/
uncommitted/
config_variables.yml
data_docs/
local_site/
index.html
expectations/
Titanic/
warning.html
static/
fonts/
HKGrotesk/
HKGrotesk-Bold.otf
HKGrotesk-BoldItalic.otf
HKGrotesk-Italic.otf
HKGrotesk-Light.otf
HKGrotesk-LightItalic.otf
HKGrotesk-Medium.otf
HKGrotesk-MediumItalic.otf
HKGrotesk-Regular.otf
HKGrotesk-SemiBold.otf
HKGrotesk-SemiBoldItalic.otf
images/
favicon.ico
glossary_scroller.gif
iterative-dev-loop.png
logo-long-vector.svg
logo-long.png
short-logo-vector.svg
short-logo.png
validation_failed_unexpected_values.gif
styles/
data_docs_custom_styles_template.css
data_docs_default_styles.css
validations/
Titanic/
warning/
20190926T134241.000000Z/
20190926T134241.000000Z/
foobarbazguid.html
validations/
.ge_store_backend_id
Titanic/
warning/
20190926T134241.000000Z/
20190926T134241.000000Z/
foobarbazguid.json
"""
)
assert mock_emit.call_count == 9
assert mock_emit.call_args_list[1] == mock.call(
{
"event_payload": {"api_version": "v2"},
"event": "cli.init.create",
"success": True,
}
)
assert_no_logging_messages_or_tracebacks(caplog, result)
def test_cli_init_connection_string_non_working_db_connection_instructs_user_and_leaves_entries_in_config_files_for_debugging(
mock_webbrowser, caplog, tmp_path_factory, sa
):
root_dir = tmp_path_factory.mktemp("bad_con_string_test")
root_dir = str(root_dir)
os.chdir(root_dir)
runner = CliRunner(mix_stderr=False)
result = runner.invoke(
cli,
["init"],
input="\n\n2\n6\nmy_db\nsqlite:////not_a_real.db\n\nn\n",
catch_exceptions=False,
)
stdout = result.output
assert mock_webbrowser.call_count == 0
assert "Always know what to expect from your data" in stdout
assert "What data would you like Great Expectations to connect to" in stdout
assert "Which database backend are you using" in stdout
assert "What is the url/connection string for the sqlalchemy connection" in stdout
assert "Give your new Datasource a short name" in stdout
assert "Attempting to connect to your database. This may take a moment" in stdout
assert "Cannot connect to the database" in stdout
assert "Profiling" not in stdout
assert "Building" not in stdout
assert "Data Docs" not in stdout
assert "Great Expectations is now set up" not in stdout
assert result.exit_code == 1
ge_dir = os.path.join(root_dir, DataContext.GE_DIR)
assert os.path.isdir(ge_dir)
config_path = os.path.join(ge_dir, DataContext.GE_YML)
assert os.path.isfile(config_path)
config = yaml.load(open(config_path))
assert config["datasources"] == {
"my_db": {
"data_asset_type": {
"module_name": None,
"class_name": "SqlAlchemyDataset",
},
"credentials": "${my_db}",
"class_name": "SqlAlchemyDatasource",
"module_name": "great_expectations.datasource",
}
}
config_path = os.path.join(
ge_dir, DataContext.GE_UNCOMMITTED_DIR, "config_variables.yml"
)
config = yaml.load(open(config_path))
assert config["my_db"] == {"url": "sqlite:////not_a_real.db"}
obs_tree = gen_directory_tree_str(os.path.join(root_dir, "great_expectations"))
assert (
obs_tree
== """\
great_expectations/
.gitignore
great_expectations.yml
checkpoints/
expectations/
.ge_store_backend_id
notebooks/
pandas/
validation_playground.ipynb
spark/
validation_playground.ipynb
sql/
validation_playground.ipynb
plugins/
custom_data_docs/
renderers/
styles/
data_docs_custom_styles.css
views/
uncommitted/
config_variables.yml
data_docs/
validations/
.ge_store_backend_id
"""
)
assert_no_logging_messages_or_tracebacks(caplog, result)
