def download(dataset, path='./', quiet=False, subdir=False, debug=False):
"""Download scripts for retriever."""
args = {
'dataset': dataset,
'command': 'download',
'path': path,
'subdir': subdir,
'quiet': quiet
}
engine = choose_engine(args)
scripts = name_matches(script_list, args['dataset'])
if scripts:
for script in scripts:
print("=> Downloading", script.name)
try:
script.download(engine, debug=debug)
script.engine.final_cleanup()
except Exception as e:
print(e)
if debug:
raise
else:
message = "The dataset \"{}\" isn't currently available in the Retriever. " \
"Run retriever.datasets() to see a list of currently " \
"available datasets".format(args['dataset'])
raise ValueError(message)
def _install(args, use_cache, debug):
"""Install datasets for retriever."""
engine = choose_engine(args)
engine.use_cache = use_cache
script_list = SCRIPT_LIST()
if not script_list or not os.listdir(SCRIPT_WRITE_PATH):
check_for_updates()
script_list = SCRIPT_LIST(force_compile=False)
data_sets_scripts = name_matches(script_list, args['dataset'])
if data_sets_scripts:
for data_sets_script in data_sets_scripts:
print("=> Installing", data_sets_script.name)
try:
data_sets_script.download(engine, debug=debug)
data_sets_script.engine.final_cleanup()
except Exception as e:
print(e)
if debug:
raise
else:
message = "The dataset \"{}\" isn't available in the Retriever. " \
"Run retriever.datasets()to list the currently available " \
"datasets".format(args['dataset'])
raise ValueError(message)
def _install(args, use_cache, debug):
"""Install datasets for retriever."""
engine = choose_engine(args)
engine.use_cache = use_cache
script_list = SCRIPT_LIST()
if not script_list or not os.listdir(SCRIPT_WRITE_PATH):
check_for_updates()
script_list = SCRIPT_LIST(force_compile=False)
data_sets_scripts = name_matches(script_list, args['dataset'])
if data_sets_scripts:
for data_sets_script in data_sets_scripts:
print("=> Installing", data_sets_script.name)
try:
data_sets_script.download(engine, debug=debug)
data_sets_script.engine.final_cleanup()
except Exception as e:
print(e)
if debug:
raise
else:
message = "The dataset \"{}\" isn't available in the Retriever. " \
"Run retriever.datasets()to list the currently available " \
"datasets".format(args['dataset'])
raise ValueError(message)
def main():
"""This function launches the EcoData Retriever."""
if len(sys.argv) == 1 or (len(sys.argv) > 1 and sys.argv[1] == 'gui'):
# if no command line args are passed, launch GUI
check_for_updates(graphical=False if 'darwin' in platform.platform().lower() else True)
lists = get_lists()
from retriever.app.main import launch_app
launch_app(lists)
else:
# otherwise, parse them
script_list = SCRIPT_LIST()
args = parser.parse_args()
if args.quiet:
sys.stdout = open(os.devnull, 'w')
if args.command == 'help':
parser.parse_args(['-h'])
if hasattr(args, 'compile') and args.compile:
script_list = SCRIPT_LIST(force_compile=True)
if args.command == 'update':
check_for_updates(graphical=False)
script_list = SCRIPT_LIST()
return
elif args.command == 'citation':
if args.dataset is None:
citation_path = os.path.join(os.path.split(__file__)[0], '../CITATION')
print citation_path
with open(citation_path) as citation_file:
print citation_file.read()
else:
scripts = name_matches(script_list, args.dataset)
for dataset in scripts:
print dataset.description
return
elif args.command == 'gui':
lists = get_lists()
from retriever.app.main import launch_app
launch_app(lists)
return
elif args.command == 'new':
f = open(args.filename, 'w')
f.write(sample_script)
f.close()
return
if args.command == 'ls' or args.dataset is None:
import lscolumns
#If scripts have never been downloaded there is nothing to list
if not script_list:
print "No scripts are currently available. Updating scripts now..."
check_for_updates(graphical=False)
print "\n\nScripts downloaded.\n"
script_list = SCRIPT_LIST()
all_scripts = set([script.shortname for script in script_list])
all_tags = set(["ALL"] +
[tag.strip().upper() for script in script_list for tagset in script.tags for tag in tagset.split('>')])
print "Available datasets (%s):" % len(all_scripts)
lscolumns.printls(sorted(list(all_scripts), key=lambda s: s.lower()))
print "Groups:"
lscolumns.printls(sorted(list(all_tags)))
return
engine = choose_engine(args.__dict__)
if hasattr(args, 'debug') and args.debug: debug = True
else: debug = False
scripts = name_matches(script_list, args.dataset)
if scripts:
for dataset in scripts:
print "=> Installing", dataset.name
try:
dataset.download(engine, debug=debug)
dataset.engine.final_cleanup()
except KeyboardInterrupt:
pass
except Exception as e:
print e
if debug: raise
print "Done!"
else:
print "The dataset %s isn't currently available in the Retriever" % (args.dataset)
print "Run 'retriever -ls to see a list of currently available datasets"
def main():
"""This function launches the Data Retriever."""
sys.argv[1:] = [arg.lower() for arg in sys.argv[1:]]
if len(sys.argv) == 1:
# if no command line args are passed, show the help options
parser.parse_args(['-h'])
else:
# otherwise, parse them
script_list = SCRIPT_LIST()
args = parser.parse_args()
if args.command == "install" and not args.engine:
parser.parse_args(['install', '-h'])
if args.quiet:
sys.stdout = open(os.devnull, 'w')
if args.command == 'help':
parser.parse_args(['-h'])
if hasattr(args, 'compile') and args.compile:
script_list = SCRIPT_LIST(force_compile=True)
if args.command == 'defaults':
for engine_item in engine_list:
print("Default options for engine ", engine_item.name)
for default_opts in engine_item.required_opts:
print(default_opts[0], " ", default_opts[2])
print()
return
if args.command == 'update':
check_for_updates(False)
script_list = SCRIPT_LIST()
return
elif args.command == 'citation':
if args.dataset is None:
print("\nCitation for retriever:\n")
print(CITATION)
else:
scripts = name_matches(script_list, args.dataset)
for dataset in scripts:
print("\nDataset: {}".format(dataset.name))
print("Citation: {}".format(dataset.citation))
print("Description: {}\n".format(dataset.description))
return
elif args.command == 'license':
dataset_license = license(args.dataset)
if dataset_license:
print(dataset_license)
else:
print("There is no license information for {}".format(args.dataset))
return
elif args.command == 'new':
f = open(args.filename, 'w')
f.write(sample_script)
f.close()
return
elif args.command == 'reset':
reset_retriever(args.scope)
return
elif args.command == 'new_json':
# create new JSON script
create_json()
return
elif args.command == 'edit_json':
# edit existing JSON script
json_file = get_script_filename(args.dataset.lower())
edit_json(json_file)
return
elif args.command == 'delete_json':
# delete existing JSON script from home directory and or script directory if exists in current dir
confirm = input("Really remove " + args.dataset.lower() +
" and all its contents? (y/N): ")
if confirm.lower().strip() in ['y', 'yes']:
json_file = get_script_filename(args.dataset.lower())
delete_json(json_file)
return
if args.command == 'ls':
# If scripts have never been downloaded there is nothing to list
if not script_list:
print("No scripts are currently available. Updating scripts now...")
check_for_updates(False)
print("\n\nScripts downloaded.\n")
if args.l is None:
all_scripts = datasets()
print("Available datasets : {}\n".format(len(all_scripts)))
from retriever import lscolumns
lscolumns.printls(dataset_names())
else:
all_scripts = datasets(args.l[0])
print("Available datasets : {}\n".format(len(all_scripts)))
count = 1
for script in all_scripts:
print("{}. {}".format(count, script.title))
print(script.name)
print(script.keywords)
print()
count += 1
return
engine = choose_engine(args.__dict__)
if hasattr(args, 'debug') and args.debug:
debug = True
else:
debug = False
sys.tracebacklimit = 0
if hasattr(args, 'debug') and args.not_cached:
engine.use_cache = False
else:
engine.use_cache = True
if args.dataset is not None:
scripts = name_matches(script_list, args.dataset)
else:
raise Exception("no dataset specified.")
if scripts:
for dataset in scripts:
print("=> Installing", dataset.name)
try:
dataset.download(engine, debug=debug)
dataset.engine.final_cleanup()
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
if debug:
raise
print("Done!")
else:
print("The dataset {} isn't currently available in the Retriever".format(
args.dataset))
print("Run 'retriever ls to see a list of currently available datasets")
def main():
"""This function launches the Data Retriever."""
if len(sys.argv) == 1:
# if no command line args are passed, show the help options
parser.parse_args(['-h'])
else:
# otherwise, parse them
script_list = SCRIPT_LIST()
args = parser.parse_args()
if args.command == "install" and not args.engine:
parser.parse_args(['install','-h'])
if args.quiet:
sys.stdout = open(os.devnull, 'w')
if args.command == 'help':
parser.parse_args(['-h'])
if hasattr(args, 'compile') and args.compile:
script_list = SCRIPT_LIST(force_compile=True)
if args.command == 'defaults':
for engine_item in engine_list:
print("Default options for engine ", engine_item.name)
for default_opts in engine_item.required_opts:
print(default_opts[0], " ", default_opts[2])
print()
return
if args.command == 'update':
check_for_updates()
script_list = SCRIPT_LIST()
return
elif args.command == 'citation':
if args.dataset is None:
print("\nCitation for retriever:\n")
print(CITATION)
else:
scripts = name_matches(script_list, args.dataset)
for dataset in scripts:
print("\nDataset: {}".format(dataset.name))
print("Citation: {}".format(dataset.citation))
print("Description: {}\n".format(dataset.description))
return
elif args.command == 'new':
f = open(args.filename, 'w')
f.write(sample_script)
f.close()
return
elif args.command == 'reset':
reset_retriever(args.scope)
return
elif args.command == 'new_json':
# create new JSON script
create_json()
return
elif args.command == 'edit_json':
# edit existing JSON script
for json_file in [filename for filename in
os.listdir(os.path.join(HOME_DIR, 'scripts')) if filename[-5:] == '.json']:
if json_file.lower().find(args.filename.lower()) != -1:
edit_json(json_file)
return
raise Exception("File not found")
elif args.command == 'delete_json':
# delete existing JSON script
for json_file in [filename for filename in
os.listdir(os.path.join(HOME_DIR, 'scripts')) if filename[-5:] == '.json']:
if json_file.lower().find(args.dataset.lower()) != -1:
confirm = input("Really remove " + json_file +
" and all its contents? (y/N): ")
if confirm.lower().strip() in ['y', 'yes']:
# raise Exception(json_file)
os.remove(os.path.join(HOME_DIR, 'scripts', json_file))
try:
os.remove(os.path.join(
HOME_DIR, 'scripts', json_file[:-4] + 'py'))
except:
# Not compiled yet
pass
return
raise Exception("File not found")
if args.command == 'ls':
# If scripts have never been downloaded there is nothing to list
if not script_list:
print("No scripts are currently available. Updating scripts now...")
check_for_updates()
print("\n\nScripts downloaded.\n")
script_list = SCRIPT_LIST()
all_scripts = []
for script in script_list:
if script.shortname:
if args.l is not None:
script_name = script.name + "\nShortname: " + script.shortname + "\n"
if script.tags:
script_name += "Tags: " + \
str([tag for tag in script.tags]) + "\n"
not_found = 0
for term in args.l:
if script_name.lower().find(term.lower()) == -1:
not_found = 1
break
if not_found == 0:
all_scripts.append(script_name)
else:
script_name = script.shortname
all_scripts.append(script_name)
all_scripts = sorted(all_scripts, key=lambda s: s.lower())
print("Available datasets : {}\n".format(len(all_scripts)))
if args.l is None:
from retriever import lscolumns
lscolumns.printls(sorted(all_scripts, key=lambda s: s.lower()))
else:
count = 1
for script in all_scripts:
print("%d. %s" % (count, script))
count += 1
return
engine = choose_engine(args.__dict__)
if hasattr(args, 'debug') and args.debug:
debug = True
else:
debug = False
sys.tracebacklimit = 0
if hasattr(args, 'debug') and args.not_cached:
use_cache = False
else:
use_cache = True
if args.dataset is not None:
scripts = name_matches(script_list, args.dataset)
else:
raise Exception("no dataset specified.")
if scripts:
for dataset in scripts:
print("=> Installing", dataset.name)
try:
dataset.download(engine, debug=debug, use_cache=use_cache)
dataset.engine.final_cleanup()
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
if debug:
raise
print("Done!")
else:
print("The dataset {} isn't currently available in the Retriever".format(
args.dataset))
print("Run 'retriever ls to see a list of currently available datasets")
def main():
"""This function launches the Data Retriever."""
if len(sys.argv) == 1:
# if no command line args are passed, show the help options
parser.parse_args(['-h'])
else:
# otherwise, parse them
script_list = SCRIPT_LIST()
args = parser.parse_args()
if args.quiet:
sys.stdout = open(os.devnull, 'w')
if args.command == 'help':
parser.parse_args(['-h'])
if hasattr(args, 'compile') and args.compile:
script_list = SCRIPT_LIST(force_compile=True)
if args.command == 'update':
check_for_updates()
script_list = SCRIPT_LIST()
return
elif args.command == 'citation':
if args.dataset is None:
citation_path = os.path.join(os.path.split(__file__)[0], '../CITATION')
print("\nCitation for retriever:\n")
with open(citation_path) as citation_file:
print(citation_file.read())
else:
scripts = name_matches(script_list, args.dataset)
for dataset in scripts:
print("\nDataset: {}".format(dataset.name))
print("Citation: {}".format(dataset.citation))
print("Description: {}\n".format(dataset.description))
return
elif args.command == 'new':
f = open(args.filename, 'w')
f.write(sample_script)
f.close()
return
elif args.command == 'reset':
reset_retriever(args.scope)
return
elif args.command == 'new_json':
# create new JSON script
create_json()
return
elif args.command == 'edit_json':
# edit existing JSON script
for json_file in [filename for filename in
os.listdir(os.path.join(HOME_DIR, 'scripts')) if filename[-5:] == '.json']:
if json_file.lower().find(args.filename.lower()) != -1:
edit_json(json_file)
return
raise Exception("File not found")
elif args.command == 'delete_json':
# delete existing JSON script
for json_file in [filename for filename in
os.listdir(os.path.join(HOME_DIR, 'scripts')) if filename[-5:] == '.json']:
if json_file.lower().find(args.dataset.lower()) != -1:
confirm = input("Really remove " + json_file +
" and all its contents? (y/N): ")
if confirm.lower().strip() in ['y', 'yes']:
# raise Exception(json_file)
os.remove(os.path.join(HOME_DIR, 'scripts', json_file))
try:
os.remove(os.path.join(
HOME_DIR, 'scripts', json_file[:-4] + 'py'))
except:
# Not compiled yet
pass
return
raise Exception("File not found")
if args.command == 'ls':
# If scripts have never been downloaded there is nothing to list
if not script_list:
print("No scripts are currently available. Updating scripts now...")
check_for_updates()
print("\n\nScripts downloaded.\n")
script_list = SCRIPT_LIST()
all_scripts = []
for script in script_list:
if script.shortname:
if args.l is not None:
script_name = script.name + "\nShortname: " + script.shortname + "\n"
if script.tags:
script_name += "Tags: " + \
str([tag for tag in script.tags]) + "\n"
not_found = 0
for term in args.l:
if script_name.lower().find(term.lower()) == -1:
not_found = 1
break
if not_found == 0:
all_scripts.append(script_name)
else:
script_name = script.shortname
all_scripts.append(script_name)
all_scripts = sorted(all_scripts, key=lambda s: s.lower())
print("Available datasets : {}\n".format(len(all_scripts)))
if args.l is None:
from retriever import lscolumns
lscolumns.printls(sorted(all_scripts, key=lambda s: s.lower()))
else:
count = 1
for script in all_scripts:
print("%d. %s" % (count, script))
count += 1
return
engine = choose_engine(args.__dict__)
if hasattr(args, 'debug') and args.debug:
debug = True
else:
debug = False
sys.tracebacklimit = 0
if args.dataset is not None:
scripts = name_matches(script_list, args.dataset)
else:
raise Exception("no dataset specified.")
if scripts:
for dataset in scripts:
print("=> Installing", dataset.name)
try:
dataset.download(engine, debug=debug)
dataset.engine.final_cleanup()
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
if debug:
raise
print("Done!")
else:
print("The dataset {} isn't currently available in the Retriever".format(
args.dataset))
print("Run 'retriever ls to see a list of currently available datasets")
def main():
"""This function launches the EcoData Retriever."""
if len(sys.argv) == 1 or (len(sys.argv) > 1 and sys.argv[1] == 'gui'):
# if no command line args are passed, launch GUI
check_for_updates(graphical=False if current_platform == 'darwin' else True)
lists = get_lists()
from retriever.app.main import launch_app
launch_app(lists)
else:
# otherwise, parse them
script_list = SCRIPT_LIST()
args = parser.parse_args()
if args.quiet:
sys.stdout = open(os.devnull, 'w')
if args.command == 'help':
parser.parse_args(['-h'])
if hasattr(args, 'compile') and args.compile:
script_list = SCRIPT_LIST(force_compile=True)
if args.command == 'update':
check_for_updates(graphical=False)
script_list = SCRIPT_LIST()
return
elif args.command == 'citation':
if args.dataset is None:
citation_path = os.path.join(os.path.split(__file__)[0], '../CITATION')
print "\nCitation for retriever:\n"
with open(citation_path) as citation_file:
print citation_file.read()
else:
scripts = name_matches(script_list, args.dataset)
for dataset in scripts:
print ("\nCitation: {}".format(dataset.citation))
print ("Description: {}\n".format(dataset.description))
return
elif args.command == 'gui':
lists = get_lists()
from retriever.app.main import launch_app
launch_app(lists)
return
elif args.command == 'new':
f = open(args.filename, 'w')
f.write(sample_script)
f.close()
return
elif args.command == 'reset':
reset_retriever(args.scope)
return
if args.command == 'ls' or args.dataset is None:
# If scripts have never been downloaded there is nothing to list
if not script_list:
print "No scripts are currently available. Updating scripts now..."
check_for_updates(graphical=False)
print "\n\nScripts downloaded.\n"
script_list = SCRIPT_LIST()
all_scripts = []
for script in script_list:
if script.name:
if args.l!=None:
script_name = script.name + "\nShortname: " + script.shortname+"\n"
if script.tags:
script_name += "Tags: "+str([tag for tag in script.tags])+"\n"
not_found = 0
for term in args.l:
if script_name.lower().find(term.lower()) == -1:
not_found = 1
break
if not_found == 0:
all_scripts.append(script_name)
else:
script_name = script.shortname
all_scripts.append(script_name)
all_scripts = sorted(all_scripts, key=lambda s: s.lower())
print "Available datasets : {}\n".format(len(all_scripts))
if args.l==None:
import lscolumns
lscolumns.printls(sorted(all_scripts, key=lambda s: s.lower()))
else:
count = 1
for script in all_scripts:
print ("%d. %s"%(count, script))
count += 1
return
engine = choose_engine(args.__dict__)
if hasattr(args, 'debug') and args.debug:
debug = True
else:
debug = False
scripts = name_matches(script_list, args.dataset)
if scripts:
for dataset in scripts:
print "=> Installing", dataset.name
try:
dataset.download(engine, debug=debug)
dataset.engine.final_cleanup()
except KeyboardInterrupt:
pass
except Exception as e:
print e
if debug: raise
print "Done!"
else:
print "The dataset {} isn't currently available in the Retriever".format(args.dataset)
print "Run 'retriever ls to see a list of currently available datasets"
def main():
"""This function launches the Data Retriever."""
sys.argv[1:] = [arg.lower() for arg in sys.argv[1:]]
if len(sys.argv) == 1:
# if no command line args are passed, show the help options
parser.parse_args(['-h'])
else:
# otherwise, parse them
if not os.path.isdir(SCRIPT_SEARCH_PATHS[1]) and not \
[f for f in os.listdir(SCRIPT_SEARCH_PATHS[-1])
if os.path.exists(SCRIPT_SEARCH_PATHS[-1])]:
check_for_updates()
script_list = SCRIPT_LIST()
args = parser.parse_args()
if args.command == "install" and not args.engine:
parser.parse_args(['install', '-h'])
if args.quiet:
sys.stdout = open(os.devnull, 'w')
if args.command == 'help':
parser.parse_args(['-h'])
if hasattr(args, 'compile') and args.compile:
script_list = SCRIPT_LIST(force_compile=True)
if args.command == 'defaults':
for engine_item in engine_list:
print("Default options for engine ", engine_item.name)
for default_opts in engine_item.required_opts:
print(default_opts[0], " ", default_opts[2])
print()
return
if args.command == 'update':
check_for_updates(False)
script_list = SCRIPT_LIST()
return
elif args.command == 'citation':
if args.dataset is None:
print("\nCitation for retriever:\n")
print(CITATION)
else:
scripts = name_matches(script_list, args.dataset)
for dataset in scripts:
print("\nDataset: {}".format(dataset.name))
print("Citation: {}".format(dataset.citation))
print("Description: {}\n".format(dataset.description))
return
elif args.command == 'license':
dataset_license = license(args.dataset)
if dataset_license:
print(dataset_license)
else:
print("There is no license information for {}".format(args.dataset))
return
elif args.command == 'new':
f = open(args.filename, 'w')
f.write(sample_script)
f.close()
return
elif args.command == 'reset':
reset_retriever(args.scope)
return
elif args.command == 'new_json':
# create new JSON script
create_json()
return
elif args.command == 'edit_json':
# edit existing JSON script
json_file = get_script_filename(args.dataset.lower())
edit_json(json_file)
return
elif args.command == 'delete_json':
# delete existing JSON script from home directory and or script directory if exists in current dir
confirm = input("Really remove " + args.dataset.lower() +
" and all its contents? (y/N): ")
if confirm.lower().strip() in ['y', 'yes']:
json_file = get_script_filename(args.dataset.lower())
delete_json(json_file)
return
if args.command == 'ls':
# If scripts have never been downloaded there is nothing to list
if not script_list:
print("No scripts are currently available. Updating scripts now...")
check_for_updates(False)
print("\n\nScripts downloaded.\n")
if args.l is None:
all_scripts = datasets()
print("Available datasets : {}\n".format(len(all_scripts)))
from retriever import lscolumns
lscolumns.printls(dataset_names())
else:
all_scripts = datasets(args.l[0])
print("Available datasets : {}\n".format(len(all_scripts)))
count = 1
for script in all_scripts:
print("{}. {}".format(count, script.title))
print(script.name)
print(script.keywords)
print()
count += 1
return
engine = choose_engine(args.__dict__)
if hasattr(args, 'debug') and args.debug:
debug = True
else:
debug = False
sys.tracebacklimit = 0
if hasattr(args, 'debug') and args.not_cached:
engine.use_cache = False
else:
engine.use_cache = True
if args.dataset is not None:
scripts = name_matches(script_list, args.dataset)
else:
raise Exception("no dataset specified.")
if scripts:
for dataset in scripts:
print("=> Installing", dataset.name)
try:
dataset.download(engine, debug=debug)
dataset.engine.final_cleanup()
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
if debug:
raise
print("Done!")
else:
print("The dataset {} isn't currently available in the Retriever".format(
args.dataset))
print("Run 'retriever ls to see a list of currently available datasets")
