def test_default_database_dir_noenv(self):
saved_env = os.environ.get('DAMMIT_DB_DIR', None)
try:
del os.environ['DAMMIT_DB_DIR']
except KeyError:
pass
result = databases.default_database_dir(self.logger)
expected = path.expanduser('~/.dammit/databases')
assert result == expected
if saved_env is not None:
os.environ['DAMMIT_DB_DIR'] = saved_env
def setup_method(self):
self.logger = logging.getLogger('tests.test_databases.TestDatabases')
class Args(object):
pass
self.args = Args()
self.args.database_dir = databases.default_database_dir(self.logger)
self.args.verbosity = 2
self.args.full = False
self.args.n_threads = 1
self.args.busco_group = 'metazoa'
self.config, self.databases = get_config()
self.config.update(vars(self.args))
self.handler = databases.get_handler(self.config)
databases.build_default_pipeline(self.handler,
self.config,
self.databases,
with_uniref=False)
def add_common_args(parser):
''' Add shared options to a parser.
Shared options are added this way instead of to the main parser
because I'd rather they come after the subcommand name.
Args:
parser (object): The parser to which arguments will be added.
'''
parser.add_argument('--database-dir',
default=databases.default_database_dir(self.logger),
help='Directory to store databases. Existing'\
' databases will not be overwritten.'\
' By default, the database directory is'\
' $HOME/.dammit/databases.'
)
parser.add_argument('--busco-group',
default='metazoa',
metavar='[metazoa, eukaryota, vertebrata, ...]',
choices=list(self.databases_d['BUSCO'].keys()),
help='Which BUSCO group to use. Should be chosen'\
' based on the organism being annotated.'\
' Full list of options is below.'
)
parser.add_argument('--n_threads',
type=int,
default=1,
help='For annotate, number of threads to pass to '\
'programs supporting multithreading. For '\
'databases, number of simultaneous tasks '\
'to execute.'
)
parser.add_argument('--config-file',
help='A JSON file providing values to override'\
' built-in config. Advanced use only!'
)
parser.add_argument('--busco-config-file',
help='Path to an alternative BUSCO config'\
' file; otherwise, BUSCO will attempt'\
' to use its default installation'\
' which will likely only work on'\
' bioconda. Advanced use only!')
parser.add_argument('--verbosity',
default=0,
type=int,
choices=[0, 1, 2],
help='Verbosity level for doit tasks.')
parser.add_argument('--profile',
default=False,
action='store_true',
help='Profile task execution.')
parser.add_argument('--force',
default=False,
action='store_true',
help='Ignore missing database tasks.')
parser.add_argument('--no_rename',
default=False,
action='store_true',
help='Keep original transcript names.'\
' Note: make sure your transcript names'\
' do not contain unusual characters.')
pgroup = parser.add_mutually_exclusive_group()
pgroup.add_argument('--full',
action='store_true',
default=False,
help='Run a "complete" annotation; includes'\
' uniref90, which is left out of the'\
' default pipeline because it is huge'\
' and homology searches take a long'\
' time.'
)
pgroup.add_argument('--nr',
action='store_true',
default=False,
help='Also include annotation to NR database, which'\
' is left out of the default and "full"'\
' pipelines because it is huge and'\
' homology searches take a long time.'
)
pgroup.add_argument('--quick',
default=False,
action='store_true',
help='Run a "quick" annotation; excludes'\
' the Infernal Rfam tasks, the HMMER'\
' Pfam tasks, and the LAST OrthoDB'\
' and uniref90 tasks. Best for users'\
' just looking to get basic stats'\
' and conditional reciprocal best'\
' LAST from a protein database.')