def execute_pipeline(self):
self.bonobo_parser = bonobo.get_argument_parser()
with bonobo.parse_args(self.bonobo_parser) as options:
bonobo.run(
self.build_graph(**options),
services=self.get_services(**options))
def run_etl(input_file_path, config_file, output_cube_path=None, cube_config=None):
"""
Run ETl Process for passed excel file.
:param input_file_path: excel file path
:param config_file: config file path
example of config::
# in the config file you specify for each table, columns associate with it.
Facts: [Price, Quantity]
Accounts: ['Source Account', 'Destination Account']
Client: ['Client Activity', 'Client Role']
:param output_cube_path: cube folder path
:param cube_config: if you want to call run_etl as function, you can pass dict config directly as param,
there an example::
@click.command()
@click.pass_context
def myETL(ctx):
# demo run_etl as function with config as dict
config = {
'Facts': ['Amount', 'Count'],
'Geography': ['Continent', 'Country', 'City'],
'Product': ['Company', 'Article', 'Licence'],
'Date': ['Year', 'Quarter', 'Month', 'Day']
}
ctx.invoke(run_etl, input_file_path='sales.xlsx', cube_config=config, output_cube_path='cube2')
"""
parser = bonobo.get_argument_parser()
parser.add_argument("-in", "--input_file_path", help="Input file")
parser.add_argument("-cf", "--config_file", help="Configuration file path")
parser.add_argument("-out", "--output_cube_path", help="Cube export path")
with bonobo.parse_args(parser) as options:
if cube_config:
options["cube_config"] = cube_config
elif config_file:
with open(config_file) as config_file:
options["cube_config"] = yaml.load(config_file)
else:
raise Exception("Config file is not specified")
if input_file_path:
options["input_file_path"] = input_file_path
else:
raise Exception("Excel file is not specified")
if output_cube_path:
options["output_cube_path"] = output_cube_path
else:
options["output_cube_path"] = os.path.join(
expanduser("~"), "olapy-data", "cubes", Path(input_file_path).stem
)
bonobo.run(get_graph(**options), services=get_services(**options))
def main(setting, ckan_portal, dataset_id, ressource, namespace, filename):
parser = bonobo.get_argument_parser()
with bonobo.parse_args(parser) as options:
bonobo.run(
get_graph(ckan_portal, dataset_id, ressource, namespace, filename, **options),
services=get_services(setting, **options)
)
def get_argument_parser(parser=None):
"""Extend CLI parser provided by bobobo and returns it."""
parser = bonobo.get_argument_parser(parser=parser)
parser.add_argument("--input_file", "-i", type=str, default=None, help="Path of the input file.")
parser.add_argument("--output_file", "-o", type=str, default=None, help="Path of the output file.")
return parser
def main():
"""Execute the pipeline graph"""
# logfilename = "wh.log"
# logger = logging.getLogger()
# ch = logging.FileHandler(logfilename)
# formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
# ch.setFormatter(formatter)
# logger.addHandler(ch)
parser = bonobo.get_argument_parser()
with bonobo.parse_args(parser) as options:
bonobo.run(get_graph(**options), services=get_services(**options))
def get_argument_parser(parser=None):
"""Extend CLI parser provided by bobobo and returns it."""
parser = bonobo.get_argument_parser(parser=parser)
parser.add_argument("--input_file", "-i", type=str, default=None, help="Path of the input file.")
parser.add_argument("--output_file", "-o", type=str, default=None, help="Path of the output file.")
# these parameters are added for accessing different S3 services
parser.add_argument("--bucket", "-b", type=str, default=None, help="Bucket name in S3 service.")
parser.add_argument("--key", "-k", type=str, default=None, help="Key to access S3 service.")
parser.add_argument("--secret_key", "-sk", type=str, default=None, help="Secret key to access the S3 service.")
parser.add_argument("--endpoint_url", "-ep", type=str, default=None, help="Endpoint URL for S3 service.")
return parser
def get_argument_parser(parser=None):
parser = bonobo.get_argument_parser(parser=parser)
parser.add_argument('--limit',
'-l',
type=int,
default=None,
help='If set, limits the number of processed lines.')
parser.add_argument(
'--print',
'-p',
action='store_true',
default=False,
help='If set, pretty prints before writing to output file.')
return parser
def get_argument_parser(parser=None):
parser = bonobo.get_argument_parser(parser=parser)
parser.add_argument(
'--limit',
'-l',
type=int,
default=None,
help='If set, limits the number of processed lines.'
)
parser.add_argument(
'--print',
'-p',
action='store_true',
default=False,
help='If set, pretty prints before writing to output file.'
)
return parser
def parse_args(parser=None):
parser = parser or bonobo.get_argument_parser()
parser.add_argument('--drop', '-D', action='store_true')
parser.add_argument('--create', '-C', action='store_true')
parser.add_argument('--echo', action='store_true')
with bonobo.parse_args(parser) as options:
import models
import settings
import services
if options['echo']:
logging.getLogger('sqlalchemy.engine').setLevel(logging.INFO)
if options['drop'] or options['create']:
root_engine = services.create_engine(superuser=True)
if options['drop']:
# drop database/role with super user privileges
_execute_sql(root_engine,
"DROP DATABASE {}".format(settings.DATABASE_NAME))
_execute_sql(root_engine,
"DROP ROLE {}".format(settings.DATABASE_USERNAME))
if options['create']:
# create database/role with super user privileges
_execute_sql(
root_engine,
'CREATE ROLE {} WITH LOGIN PASSWORD \'{}\';'.format(
settings.DATABASE_USERNAME,
settings.DATABASE_PASSWORD))
_execute_sql(
root_engine,
'CREATE DATABASE {} WITH OWNER={} TEMPLATE=template0 ENCODING="utf-8";'
.format(settings.DATABASE_NAME,
settings.DATABASE_USERNAME))
# create tables in userland
engine = services.create_engine()
models.metadata.create_all(engine)
yield options
def get_argument_parser(parser=None):
parser = bonobo.get_argument_parser(parser=parser)
parser.add_argument("--limit",
"-l",
type=int,
default=None,
help="If set, limits the number of processed lines.")
parser.add_argument(
"--print",
"-p",
action="store_true",
default=False,
help="If set, pretty prints before writing to output file.")
parser.add_argument("--strategy",
"-s",
type=str,
choices=STRATEGIES.keys(),
default=DEFAULT_STRATEGY)
return parser
import bonobo
from bonobo.examples.files._services import get_services
def get_graph(*, _limit=None, _print=False):
return bonobo.Graph(
bonobo.CsvReader('datasets/coffeeshops.txt'),
*((bonobo.Limit(_limit), ) if _limit else ()),
*((bonobo.PrettyPrinter(), ) if _print else ()),
bonobo.CsvWriter('coffeeshops.csv', fs='fs.output')
)
if __name__ == '__main__':
parser = bonobo.get_argument_parser()
parser.add_argument(
'--limit',
'-l',
type=int,
default=None,
help='If set, limits the number of processed lines.'
)
parser.add_argument(
'--print',
'-p',
action='store_true',
default=False,
help='If set, pretty prints before writing to output file.'
)
def create_parser(self, prog_name, subcommand):
return bonobo.get_argument_parser(super().create_parser(
prog_name, subcommand))
def parse_args(mixed=None):
"""
Context manager to extract and apply environment related options from the provided argparser result.
A dictionnary with unknown options will be yielded, so the remaining options can be used by the caller.
:api: bonobo.patch_environ
:param mixed: ArgumentParser instance, Namespace, or dict.
:return:
"""
if mixed is None:
global _parser
if _parser is not None:
warnings.warn(
'You are calling bonobo.parse_args() without a parser argument, but it looks like you created a parser before. You probably want to pass your parser to this call, or if creating a new parser here is really what you want to do, please create a new one explicitely to silence this warning.'
)
# use the api from bonobo namespace, in case a command patched it.
import bonobo
mixed = bonobo.get_argument_parser()
if isinstance(mixed, argparse.ArgumentParser):
options = mixed.parse_args()
else:
options = mixed
if not isinstance(options, dict):
options = options.__dict__
# make a copy so we don't polute our parent variables.
options = dict(options)
# storage for values before patch.
_backup = {}
# Priority order: --env > --env-file > system > --default-env > --default-env-file
#
# * The code below is reading default-env before default-env-file as if the first sets something, default-env-file
# won't override it.
# * Then, env-file is read from before env, as the behaviour will be the oposite (env will override a var even if
# env-file sets something.)
try:
# Set default environment
for name, value in map(parse_var, options.pop('default_env', []) or []):
if not name in os.environ:
if not name in _backup:
_backup[name] = os.environ.get(name, None)
os.environ[name] = value
# Read and set default environment from file(s)
for filename in options.pop('default_env_file', []) or []:
for name, value in load_env_from_file(filename):
if not name in os.environ:
if not name in _backup:
_backup[name] = os.environ.get(name, None)
os.environ[name] = value
# Read and set environment from file(s)
for filename in options.pop('env_file', []) or []:
for name, value in load_env_from_file(filename):
if not name in _backup:
_backup[name] = os.environ.get(name, None)
os.environ[name] = value
# Set environment
for name, value in map(parse_var, options.pop('env', []) or []):
if not name in _backup:
_backup[name] = os.environ.get(name, None)
os.environ[name] = value
yield options
finally:
for name, value in _backup.items():
if value is None:
del os.environ[name]
else:
os.environ[name] = value
def get_argument_parser(argparser):
"""Augments the given ArgumentParser for use with the Bonobo ETL framework."""
return bonobo.get_argument_parser(parser=argparser)
def main(setting, query, namespace, filename):
parser = bonobo.get_argument_parser()
with bonobo.parse_args(parser) as options:
bonobo.run(get_graph(query, namespace, filename, **options),
services=get_services(setting, **options))
def create_parser(self, prog_name, subcommand):
return bonobo.get_argument_parser(super().create_parser(prog_name, subcommand))
def load(result):
# Cada resultado que ingrese a este punto
# ingresarlo como una nueva linea a un archivo
# de texto (usando open con 'a' y write)
# o insertando a una base de datos a elección.
# El objetivo es que quede almacenado en un archivo
# o una base de datos la tabla del 5
cinco.insert_multiplo(result)
print('Fin!')
def get_graph(**options):
graph = bonobo.Graph()
graph.add_chain(extract, transform, load)
return graph
def get_services(**options):
return {}
if __name__ == "__main__":
cinco.create_schema()
parser = bonobo.get_argument_parser()
with bonobo.parse_args(parser) as options:
bonobo.run(get_graph(**options), services=get_services(**options))
def main():
"""Execute the pipeline graph
"""
parser = bonobo.get_argument_parser()
with bonobo.parse_args(parser) as options:
bonobo.run(get_graph(**options), services=get_services(**options))
