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():
import argparse
bp_formats = ' | '.join(bp._io.supported_formats)
input_formats = bp_formats
output_formats = '%s | ascii' % bp_formats
parser = argparse.ArgumentParser()
parser.add_argument('--version', action='version', version=__version__)
parser.add_argument('-v', '--verbose', action='store_true', help='write out SPARQL queries before executing')
parser.add_argument('-s', '--store', help='name of Redland store (default=virtuoso)')
parser.add_argument('-d', '--dsn', help='ODBC DSN (default=Virtuoso)')
parser.add_argument('-u', '--user', help='ODBC user (default=dba)')
parser.add_argument('-p', '--password', help='ODBC password (default=dba)')
subparsers = parser.add_subparsers(help='sub-command help', dest='command')
# treestore add: add trees to the database
add_parser = subparsers.add_parser('add', help='add trees to treestore')
add_parser.add_argument('file', help='tree file')
add_parser.add_argument('uri', help='tree uri (default=file name)', nargs='?', default=None)
add_parser.add_argument('-f', '--format', help='file format (%s)' % input_formats,
nargs='?', default='newick')
add_parser.add_argument('--rooted', help='this is a rooted tree', action='store_true')
add_parser.add_argument('--taxonomy', help="the URI of a taxonomy graph to label higher-order taxa",
nargs='?', default=None)
add_parser.add_argument('--tax-root', help="the name of the top-most taxonomic group in the tree, used to subset the taxonomy and avoid homonymy issues",
nargs='?', default=None)
# treestore get: download an entire tree
get_parser = subparsers.add_parser('get', help='retrieve trees from treestore')
get_parser.add_argument('uri', help='tree uri')
get_parser.add_argument('-f', '--format', help='serialization format (%s) (default=newick)' % output_formats,
nargs='?', default='newick')
# treestore rm: delete trees from the database
rm_parser = subparsers.add_parser('rm', help='remove trees from treestore')
rm_parser.add_argument('uri', help='tree uri')
# treestore ls: list trees
ls_parser = subparsers.add_parser('ls', help='list all trees in treestore')
ls_parser.add_argument('contains', help='comma-delimited list of desired taxa',
nargs='?', default='')
ls_parser.add_argument('--counts', help="display the number of matched taxa next to each tree URI",
action='store_true')
ls_parser.add_argument('-l', help="list one per line; don't try to pretty-print",
action='store_true')
ls_parser.add_argument('-f', help="show full URIs instead of just IDs",
action='store_true')
ls_parser.add_argument('--taxonomy', help="the URI of a taxonomy graph to enable synonymy lookup",
nargs='?', default=None)
ls_parser.add_argument('--filter', help="SPARQL graph pattern that returned trees must match",
nargs='?', default=None)
# treestore names: get list of taxa contained in a tree
names_parser = subparsers.add_parser('names',
help='return a comma-separated list of all taxa names')
names_parser.add_argument('uri', help='tree uri (default=all trees)',
nargs='?', default=None)
names_parser.add_argument('-f', '--format', help='file format (json, csv, xml) (default=csv)',
default='csv')
# treestore count: count the number of labeled nodes
count_parser = subparsers.add_parser('count',
help='returns the number of labeled nodes in a tree')
count_parser.add_argument('uri', help='tree uri (default=all trees)',
nargs='?', default=None)
# treestore query: create a subtree from a list of taxa
query_parser = subparsers.add_parser('query',
help='retrieve the best subtree containing a given set of taxa')
query_parser.add_argument('contains', help='comma-delimited list of desired taxa',
nargs='?')
query_parser.add_argument('uri', help='tree uri (default=select automatically)',
nargs='?', default=None)
query_parser.add_argument('-f', '--format', help='serialization format (%s) (default=newick)' % output_formats,
nargs='?', default='newick')
query_parser.add_argument('--complete', help="return complete subtree from MRCA; don't prune other taxa from the resulting tree",
action='store_true')
query_parser.add_argument('--taxonomy', help="the URI of a taxonomy graph to enable synonymy lookup",
nargs='?', default=None)
query_parser.add_argument('--filter', help="SPARQL graph pattern that returned trees must match",
nargs='?', default=None)
# treestore annotate: add metadata annotations to tree
ann_parser = subparsers.add_parser('annotate', help='annotate tree with triples from RDF file')
ann_parser.add_argument('uri', help='tree uri', default=None)
ann_parser.add_argument('--file', help='annotation file')
ann_parser.add_argument('--text', help='annotation, in turtle format', default=None)
ann_parser.add_argument('--doi', help='tree source DOI', default=None)
args = parser.parse_args()
if args.dsn: kwargs['dsn'] = args.dsn
if args.user: kwargs['user'] = args.user
if args.password: kwargs['password'] = args.password
elif not 'password' in kwargs: password = getpass()
kwargs['verbose'] = args.verbose
treestore = Treestore(**kwargs)
if args.command == 'add':
# parse a tree and add it to the treestore
treestore.add_trees(args.file, args.format, args.uri, rooted=args.rooted,
taxonomy=args.taxonomy, tax_root=args.tax_root)
elif args.command == 'get':
# get a tree, serialize in specified format, and output to stdout
treestore.serialize_trees(args.uri, args.format, handle=sys.stdout)
elif args.command == 'rm':
# remove a certain tree from the treestore
treestore.remove_trees(args.uri)
elif args.command == 'ls':
# list all trees in the treestore or trees containing a list of taxa
contains = args.contains
if contains:
contains = set([s.strip() for s in contains.split(',')])
trees = list(treestore.list_trees_containing_taxa(
contains=contains, taxonomy=args.taxonomy,
show_counts=args.counts, filter=args.filter))
if args.counts: trees = ['%s (%s)' % tree for tree in trees]
else: trees = [str(x) for x in trees]
else:
trees = list(treestore.list_trees(filter=args.filter))
if not trees: exit()
if not args.f:
trees = [treestore.id_from_uri(x) for x in trees]
if args.l:
print '\n'.join(trees)
else:
import lscolumns
lscolumns.printls(trees)
elif args.command == 'names':
print treestore.get_names(tree_uri=args.uri, format=args.format)
elif args.command == 'count':
print len([r for r in treestore.get_names(tree_uri=args.uri, format=None)])
elif args.command == 'query':
contains = set([s.strip() for s in args.contains.split(',')])
treestore.get_subtree(contains=contains, tree_uri=args.uri,
format=args.format,
prune=not args.complete,
taxonomy=treestore.uri_from_id(args.taxonomy) if args.taxonomy else None,
filter=args.filter,
handle=sys.stdout,
)
elif args.command == 'annotate':
treestore.annotate(args.uri, annotations=args.text, annotation_file=args.file, doi=args.doi)
def main():
import argparse
bp_formats = ' | '.join(bp._io.supported_formats)
input_formats = bp_formats
output_formats = '%s | ascii' % bp_formats
parser = argparse.ArgumentParser()
parser.add_argument('-v', '--version', action='version', version=__version__)
parser.add_argument('-s', '--store', help='name of Redland store (default=virtuoso)')
parser.add_argument('-d', '--dsn', help='ODBC DSN (default=Virtuoso)')
parser.add_argument('-u', '--user', help='ODBC user (default=dba)')
parser.add_argument('-p', '--password', help='ODBC password (default=dba)')
subparsers = parser.add_subparsers(help='sub-command help', dest='command')
add_parser = subparsers.add_parser('add', help='add trees to treestore')
add_parser.add_argument('file', help='tree file')
add_parser.add_argument('format', help='file format (%s)' % input_formats)
add_parser.add_argument('uri', help='tree uri (default=file name)', nargs='?', default=None)
add_parser.add_argument('--bulk', help='use the virtuoso bulk loader', action='store_true')
add_parser.add_argument('--puid', help='create a pseudo-unique ID for the tree', action='store_true')
add_parser.add_argument('--rooted', help='this is a rooted tree', action='store_true')
get_parser = subparsers.add_parser('get', help='retrieve trees from treestore')
get_parser.add_argument('uri', help='tree uri')
get_parser.add_argument('format', help='serialization format (%s) (default=newick)' % output_formats,
nargs='?', default='newick')
rm_parser = subparsers.add_parser('rm', help='remove trees from treestore')
rm_parser.add_argument('uri', help='tree uri')
ls_parser = subparsers.add_parser('ls', help='list all trees in treestore')
ls_parser.add_argument('contains',
help='comma-delimited list of species that must be contained in each returned tree (default=none)',
nargs='?', default='')
ls_parser.add_argument('--all', help='only return trees that contain all given species',
action='store_true')
names_parser = subparsers.add_parser('names',
help='return a comma-separated list of all taxa names')
names_parser.add_argument('uri', help='tree uri (default=all trees)',
nargs='?', default=None)
names_parser.add_argument('-f', '--format', help='file format (json, csv, xml) (default=csv)',
default='csv')
count_parser = subparsers.add_parser('count',
help='returns the number of labelled nodes in a tree')
count_parser.add_argument('uri', help='tree uri (default=all trees)',
nargs='?', default=None)
query_parser = subparsers.add_parser('query',
help='retrieve the best subtree containing a given set of taxa')
query_parser.add_argument('contains',
help='comma-delimited list of species that must be contained in each returned tree',
nargs='?')
query_parser.add_argument('format', help='serialization format (%s) (default=newick)' % output_formats,
nargs='?', default='newick')
query_parser.add_argument('uri', help='tree uri (default=select automatically)',
nargs='?', default=None)
query_parser.add_argument('--all', help='only return trees that contain all given species',
action='store_true')
query_parser.add_argument('--complete', help="return complete subtree from MRCA; don't prune other taxa from the resulting tree",
action='store_true')
ann_parser = subparsers.add_parser('annotate', help='annotate tree with triples from RDF file')
ann_parser.add_argument('file', help='annotation file')
ann_parser.add_argument('format', help='annotation file format (default=ntriples)')
ann_parser.add_argument('uri', help='tree uri', default=None)
args = parser.parse_args()
kwargs = {}
if args.store: kwargs['storage_name'] = args.store
if args.dsn: kwargs['dsn'] = args.dsn
if args.user: kwargs['user'] = args.user
if args.password: kwargs['password'] = args.password
treestore = Treestore(**kwargs)
if args.command == 'add':
# parse a tree and add it to the treestore
treestore.add_trees(args.file, args.format, args.uri, bulk_loader=args.bulk, puid=args.puid,
rooted=args.rooted)
elif args.command == 'get':
# get a tree, serialize in specified format, and output to stdout
print treestore.serialize_trees(args.uri, args.format),
elif args.command == 'rm':
# remove a certain tree from the treestore
treestore.remove_trees(args.uri)
elif args.command == 'ls':
# list all trees in the treestore or trees containing a list of taxa
contains = args.contains
if contains:
contains = set([s.strip() for s in contains.split(',')])
trees = [r for r in treestore.list_trees_containing_taxa(
contains=contains, match_all=args.all)]
else:
trees = treestore.list_trees()
if not trees: exit()
import lscolumns
lscolumns.printls(trees)
elif args.command == 'names':
print treestore.get_names(tree_uri=args.uri, format=args.format)
elif args.command == 'count':
print len([r for r in treestore.get_names(tree_uri=args.uri, format=None)])
elif args.command == 'query':
contains = set([s.strip() for s in args.contains.split(',')])
print treestore.get_subtree(contains=contains, tree_uri=args.uri,
match_all=args.all, format=args.format, prune=not args.complete),
elif args.command == 'annotate':
annotate(args.uri, args.file, treestore, format=args.format)
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"
