Files
obitools3/python/obitools3/commands/import.pyx
2016-04-26 14:29:54 +02:00

135 lines
4.5 KiB
Cython

from obitools3.apps.progress cimport ProgressBar # @UnresolvedImport
from obitools3.files.universalopener cimport uopen
from obitools3.parsers.fasta import fastaIterator
from obitools3.parsers.fastq import fastqIterator
from obitools3.obidms._obidms import OBIDMS
import time
__title__="Counts sequences in a sequence set"
default_config = { 'destview' : None,
'skip' : 0,
'only' : None,
'skiperror' : False,
'seqinformat' : None,
'moltype' : 'nuc',
'filename' : None
}
def addOptions(parser):
parser.add_argument(dest='import:filename',
metavar='<FILENAME>',
nargs='?',
default=None,
help='sequence file name to be imported' )
group=parser.add_argument_group('obi import specific options')
group.add_argument('--default-dms','-d',
action="store", dest="obi:defaultdms",
metavar='<DMS NAME>',
default=None,
type=str,
help="Name of the default DMS for reading and writing data")
group.add_argument('--destination-view','-v',
action="store", dest="import:destview",
metavar='<VIEW NAME>',
default=None,
type=str,
required=True,
help="Name of the default DMS for reading and writing data")
group=parser.add_argument_group('obi import specific options')
group.add_argument('--skip',
action="store", dest="import:skip",
metavar='<N>',
default=None,
type=int,
help="skip the N first sequences")
group.add_argument('--only',
action="store", dest="import:only",
metavar='<N>',
default=None,
type=int,
help="treat only N sequences")
group.add_argument('--skip-on-error',
action="store_true", dest="import:skiperror",
default=None,
help="Skip sequence entries with parse error")
group.add_argument('--fasta',
action="store_const", dest="import:seqinformat",
default=None,
const='fasta',
help="Input file is in fasta nucleic format (including obitools fasta extentions)")
group.add_argument('--fastq',
action="store_const", dest="import:seqinformat",
default=None,
const='fastq',
help="Input file is in sanger fastq nucleic format (standard fastq)")
group.add_argument('--nuc',
action="store_const", dest="import:moltype",
default=None,
const='nuc',
help="Input file contains nucleic sequences")
group.add_argument('--prot',
action="store_const", dest="import:moltype",
default=None,
const='pep',
help="Input file contains protein sequences")
def run(config):
pb = ProgressBar(35000000,config,seconde=5)
inputs = uopen(config['import']['filename'])
if config['import']['seqinformat']=='fasta':
iseq = fastaIterator(inputs)
view_type="NUC_SEQS_VIEW"
elif config['import']['seqinformat']=='fastq':
iseq = fastqIterator(inputs)
view_type="NUC_SEQS_VIEW"
else:
raise RuntimeError('No file format specified')
# Temporary way to handle NA values
NA_list = ["nan"]
# Create DMS
d = OBIDMS(config['obi']['defaultdms'])
# Create view
view = d.new_view(config['import']['destview'], view_type=view_type)
i = 0
for seq in iseq:
pb(i)
view[i].set_id(seq['id'])
view[i].set_definition(seq['definition'])
view[i].set_sequence(seq['sequence'])
for tag in seq['tags'] :
#print(tag, seq['tags'][tag])
#if seq['tags'][tag] not in NA_list :
view[i][tag] = seq['tags'][tag]
i+=1
print(view)
# print(view.__repr__())
view.save_and_close()
d.close()